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

    Neuronpedia

    INDEX
    Explanations

    words related to contradiction or opposing ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.17
     ÐĶив
    -0.16
    mun
    -0.15
     chua
    -0.15
    몬
    -0.14
     Div
    -0.14
    rosis
    -0.14
    ULONG
    -0.14
    ÅĻen
    -0.14
    ulong
    -0.14
    POSITIVE LOGITS
     contr
    0.22
     CONTR
    0.20
     Contr
    0.17
    ictory
    0.17
    ax
    0.16
    aven
    0.16
    ional
    0.16
    ived
    0.15
    Contr
    0.15
    aires
    0.15
    Act Density 0.017%

    No Known Activations