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

    Neuronpedia

    INDEX
    Explanations

    words related to attitudes and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zes
    -0.17
    cers
    -0.16
    jedn
    -0.16
    pez
    -0.15
    лиÑĨ
    -0.15
    cies
    -0.15
    å©·
    -0.14
    IGIN
    -0.14
    idding
    -0.14
    ej
    -0.14
    POSITIVE LOGITS
    itude
    0.38
    ending
    0.36
    itudes
    0.36
    orney
    0.35
    acking
    0.34
    endant
    0.33
    acked
    0.33
    ended
    0.31
    orneys
    0.31
    acker
    0.31
    Act Density 0.011%

    No Known Activations