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

    Neuronpedia

    INDEX
    Explanations

    specific data or numerical information related to events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ROW
    -0.15
    commercial
    -0.14
     wishes
    -0.14
     commercial
    -0.14
     Chim
    -0.14
     Tos
    -0.14
    ss
    -0.13
    erts
    -0.13
    .activ
    -0.13
     flex
    -0.13
    POSITIVE LOGITS
    eum
    0.17
    ADOS
    0.16
    jis
    0.15
    odus
    0.15
    ALSE
    0.14
    acc
    0.14
    _regularizer
    0.14
     PAC
    0.14
    asaki
    0.14
    åŁºåľ°
    0.14
    Act Density 0.002%

    No Known Activations