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

    Neuronpedia

    INDEX
    Explanations

    negations and their associated contexts in expressions of opinion and reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apus
    -0.15
    åĩ¡
    -0.14
    ASF
    -0.14
    voj
    -0.13
    ountains
    -0.13
     Wikimedia
    -0.13
    )(((
    -0.13
    zza
    -0.13
    )((((
    -0.13
    umno
    -0.12
    POSITIVE LOGITS
     either
    1.72
    either
    1.46
     Either
    1.44
     EITHER
    1.36
    Either
    1.34
     либо
    0.85
     soit
    0.73
    ither
    0.71
    ITHER
    0.62
     εί
    0.56
    Act Density 0.523%

    No Known Activations