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

    Neuronpedia

    INDEX
    Explanations

    phrases related to escalating conflicts or crises

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a full-scale conflict or crisis situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.85
     Zar
    -0.73
     Pok
    -0.71
     Phi
    -0.69
    imaru
    -0.69
     Tycoon
    -0.68
     Cah
    -0.67
     Maher
    -0.67
     Feinstein
    -0.66
     Reloaded
    -0.66
    POSITIVE LOGITS
    fledged
    1.27
    sized
    1.25
    bodied
    1.19
    function
    1.15
    hearted
    1.08
    season
    1.05
    length
    1.05
    heartedly
    1.05
    functional
    1.03
    circ
    1.03
    Act Density 0.029%

    No Known Activations