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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate conditions or dependencies in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennen
    -0.18
    amient
    -0.17
    lider
    -0.16
    clair
    -0.15
    sher
    -0.15
    aign
    -0.15
    loff
    -0.15
    .sy
    -0.14
    ovit
    -0.14
    xima
    -0.14
    POSITIVE LOGITS
    ha
    0.16
    isl
    0.16
    ÑĢаÑħ
    0.15
    aran
    0.15
    adal
    0.15
    otron
    0.14
    ik
    0.14
    adden
    0.13
     Lump
    0.13
    endl
    0.13
    Act Density 0.077%

    No Known Activations