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

    Neuronpedia

    INDEX
    Explanations

    words related to political figures or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "isl" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.77
    lishing
    -0.71
    notes
    -0.70
    cffffcc
    -0.69
    nces
    -0.67
    ccoli
    -0.67
     LIFE
    -0.65
    ilant
    -0.64
    ritic
    -0.63
    block
    -0.63
    POSITIVE LOGITS
    ipeg
    0.96
    ature
    0.92
    owsky
    0.88
    uggage
    0.88
    atures
    0.87
    ifter
    0.86
    akes
    0.85
    ative
    0.84
    iquid
    0.83
    oud
    0.82
    Act Density 0.020%

    No Known Activations