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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making or breaking situations, particularly in contexts involving deceit or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":["
    -0.64
    hov
    -0.63
    eger
    -0.62
     propensity
    -0.60
     hemor
    -0.59
    EStreamFrame
    -0.59
     coron
    -0.58
     revolving
    -0.56
    Downloadha
    -0.56
    Constructed
    -0.55
    POSITIVE LOGITS
    çİĭ
    0.78
    URE
    0.74
    estine
    0.73
     noises
    0.73
    ends
    0.70
    ota
    0.69
     Strongh
    0.68
     Murd
    0.68
    asty
    0.64
     mockery
    0.64
    Act Density 0.076%

    No Known Activations