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

    Neuronpedia

    INDEX
    Explanations

    references to political campaigns and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    olitics
    -0.68
    pack
    -0.64
    ¶
    -0.64
    lly
    -0.61
    llah
    -0.60
    nat
    -0.59
    andom
    -0.59
    wald
    -0.59
    reason
    -0.58
    plan
    -0.58
    POSITIVE LOGITS
     which
    0.85
     featuring
    0.75
     thereby
    0.74
     meanwhile
    0.71
     whose
    0.71
    Magikarp
    0.66
    which
    0.66
     whereby
    0.63
     precursor
    0.62
     wherein
    0.62
    Act Density 0.519%

    No Known Activations