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

    Neuronpedia

    INDEX
    Explanations

    instances of panic or alarming situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.19
    eming
    -0.16
    .scalablytyped
    -0.16
    'gc
    -0.16
    PÅĻi
    -0.15
    illard
    -0.15
    /cs
    -0.15
    cÃŃm
    -0.15
    umba
    -0.14
    립
    -0.14
    POSITIVE LOGITS
    ingly
    0.16
    REAK
    0.15
     ÑĤи
    0.15
    ITHER
    0.14
    165
    0.14
    ate
    0.14
    bsp
    0.14
    AME
    0.14
    ithe
    0.14
    Ú©Ùĩ
    0.14
    Act Density 0.013%

    No Known Activations