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

    Neuronpedia

    INDEX
    Explanations

    instances of fleeing or escaping actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Exacts
    -0.41
     المعيارى
    -0.39
    ganggu
    -0.36
    віч
    -0.36
     Uniform
    -0.35
    GLint
    -0.35
    uniform
    -0.34
     nmax
    -0.34
    ops
    -0.33
     ochi
    -0.33
    POSITIVE LOGITS
     away
    0.77
     departure
    0.73
     oprot
    0.71
     escape
    0.70
     Flucht
    0.69
     fleeing
    0.68
    離開
    0.67
     flee
    0.66
     leaving
    0.65
    exitRule
    0.65
    Act Density 0.423%

    No Known Activations