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

    Neuronpedia

    INDEX
    Explanations

    statements or actions by political figures

    oai_token-act-pair · gpt-3.5-turbo

    statements or actions taken by individuals in positions of authority or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.56
     stub
    -0.55
     offspring
    -0.53
    otin
    -0.52
    physical
    -0.52
     scaven
    -0.51
    respective
    -0.51
    rafted
    -0.50
    1966
    -0.49
     tag
    -0.49
    POSITIVE LOGITS
    doms
    0.73
     forcefully
    0.60
     Mattis
    0.60
     CNBC
    0.60
    İĭ
    0.59
     Talks
    0.57
     scathing
    0.57
     bluntly
    0.57
    ozy
    0.56
     Amnesty
    0.55
    Act Density 0.718%

    No Known Activations