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

    Neuronpedia

    INDEX
    Explanations

    phrases related to replacing or replacements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substitution or replacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.87
    hest
    -0.74
    insula
    -0.72
     Reasons
    -0.70
     isEnabled
    -0.65
    eca
    -0.62
    ModLoader
    -0.62
    osis
    -0.61
    keyes
    -0.61
     Proceed
    -0.60
    POSITIVE LOGITS
     obsolete
    0.81
     redundant
    0.75
    nces
    0.75
    atives
    0.75
    ments
    0.74
     bulbs
    0.72
     retiring
    0.71
    utions
    0.70
     deprecated
    0.68
    itute
    0.67
    Act Density 0.042%

    No Known Activations