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

    Neuronpedia

    INDEX
    Explanations

    words related to opposition or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERTISE
    -0.16
    ooth
    -0.15
    ting
    -0.15
    ÑĮÑĤе
    -0.15
    ql
    -0.15
    tering
    -0.14
    ricular
    -0.14
    ilarity
    -0.14
    td
    -0.14
    ees
    -0.14
    POSITIVE LOGITS
    arend
    0.20
    ort
    0.19
    ending
    0.19
    ounce
    0.18
    ense
    0.17
    ended
    0.17
    orted
    0.17
    ected
    0.16
    áÄį
    0.16
    acted
    0.15
    Act Density 0.096%

    No Known Activations