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

    Neuronpedia

    INDEX
    Explanations

    contrasting statements or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ummings
    -0.17
    idis
    -0.15
    ifer
    -0.15
    wi
    -0.15
    elize
    -0.14
    arus
    -0.14
    wie
    -0.14
    jur
    -0.14
     peers
    -0.14
    ledge
    -0.13
    POSITIVE LOGITS
     contrary
    0.30
     opposite
    0.21
    pill
    0.20
     Pill
    0.19
    zac
    0.16
    ä¿¡
    0.15
    azi
    0.15
     exact
    0.15
     contrario
    0.15
     OP
    0.15
    Act Density 0.020%

    No Known Activations