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

    Neuronpedia

    INDEX
    Explanations

    instances where something is being replaced or proposed to be replaced

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.90
    insula
    -0.76
    hest
    -0.71
     Reasons
    -0.70
    catentry
    -0.69
    Kids
    -0.66
     isEnabled
    -0.66
    reprene
    -0.64
    akra
    -0.64
    ModLoader
    -0.63
    POSITIVE LOGITS
     obsolete
    0.85
     redundant
    0.77
    atives
    0.72
     scratch
    0.71
    itute
    0.70
    nces
    0.69
    ments
    0.69
    utions
    0.68
     retiring
    0.67
     superflu
    0.67
    Act Density 0.028%

    No Known Activations