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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or caution in scenarios related to upcoming events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    c
    -0.16
    imbus
    -0.15
    ediator
    -0.15
    hood
    -0.15
    evin
    -0.15
    rish
    -0.14
    -fluid
    -0.14
    à¸Ļา
    -0.14
    fy
    -0.14
    nd
    -0.14
    POSITIVE LOGITS
    äng
    0.16
    /out
    0.16
    868
    0.16
    ãĥĮ
    0.15
    ahat
    0.15
    /back
    0.15
    egal
    0.15
    378
    0.14
    slash
    0.14
    Configurer
    0.14
    Act Density 0.014%

    No Known Activations