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

    Neuronpedia

    INDEX
    Explanations

    action verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of receiving or obtaining information or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.73
     cultivated
    -0.72
    respective
    -0.71
     foreseeable
    -0.68
     preferred
    -0.67
     TBA
    -0.65
     maintained
    -0.64
    kept
    -0.64
     uniformly
    -0.63
    often
    -0.63
    POSITIVE LOGITS
    nesday
    0.79
     Anniversary
    0.74
    lyak
    0.73
     Vlad
    0.73
    Reviewer
    0.70
     Supreme
    0.66
    iphany
    0.64
     another
    0.64
     Deadline
    0.64
     anniversary
    0.64
    Act Density 0.204%

    No Known Activations