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

    Neuronpedia

    INDEX
    Explanations

    elements of conflict in discussions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WITHOUT
    -0.19
     WITHOUT
    -0.19
    andon
    -0.16
    along
    -0.15
    enga
    -0.15
    aload
    -0.15
    íķĺëĬĶëį°
    -0.15
    ãĤ¥
    -0.14
    óst
    -0.14
    WF
    -0.14
    POSITIVE LOGITS
     nor
    1.29
    nor
    1.02
     Nor
    0.99
    Nor
    0.90
     NOR
    0.74
     neither
    0.63
     anymore
    0.61
     sondern
    0.52
     بÙĦÚ©Ùĩ
    0.46
     Neither
    0.45
    Act Density 0.465%

    No Known Activations