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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments expressing reluctance or dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sogar
    -0.15
    quip
    -0.14
    inux
    -0.14
    .actual
    -0.14
    asal
    -0.14
    adla
    -0.14
    zp
    -0.14
     dokonce
    -0.13
     nuest
    -0.13
    ittal
    -0.13
    POSITIVE LOGITS
     nor
    0.30
     Nor
    0.25
    Nor
    0.22
    nor
    0.21
     occasionally
    0.19
     anymore
    0.18
     or
    0.15
     sondern
    0.15
     occasional
    0.14
    Å¡lo
    0.14
    Act Density 0.110%

    No Known Activations