Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    prefixes indicating the beginning of sentences or new sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to decision-making regarding loan applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    approving or finalizing changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hoeddwyd
    -0.81
    enderror
    -0.76
    MessageOf
    -0.72
    +#+#
    -0.70
    SharedDtor
    -0.69
     հղումներ
    -0.64
     Roskov
    -0.64
    aarrggbb
    -0.61
     calendriers
    -0.60
    ViewFeatures
    -0.60
    POSITIVE LOGITS
     changes
    0.60
     amended
    0.55
     amendments
    0.55
     [*]
    0.52
     spending
    0.51
     Changes
    0.48
     change
    0.48
     modifications
    0.48
    changes
    0.48
    
    0.47
    Act Density 0.061%

    No Known Activations