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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating roles, responsibilities, and interactions among individuals in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccione
    -0.15
    tabpanel
    -0.15
    PPER
    -0.14
    coni
    -0.14
    ëıħ
    -0.14
    ÙħÙĬÙħ
    -0.14
    xcc
    -0.14
    ontrol
    -0.14
    ACKET
    -0.13
    urrenc
    -0.13
    POSITIVE LOGITS
    esteem
    0.18
    utherland
    0.16
     Cah
    0.16
     instead
    0.15
     Toll
    0.15
    ãĥĭãĥ¼
    0.15
    roid
    0.15
     Cover
    0.14
     Tek
    0.14
    ichten
    0.14
    Act Density 0.233%

    No Known Activations