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

    Neuronpedia

    INDEX
    Explanations

    words indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INGLE
    -0.16
    ivol
    -0.15
    holm
    -0.15
    ucci
    -0.14
    ména
    -0.14
    Ñĥков
    -0.14
    #
    -0.14
    zi
    -0.14
     Rubber
    -0.14
    Ħ
    -0.14
    POSITIVE LOGITS
     pent
    0.16
     nay
    0.15
     $.
    0.15
    rix
    0.15
    avi
    0.15
    ULSE
    0.15
     Gra
    0.14
    ÏĦαν
    0.14
    &type
    0.14
    iod
    0.14
    Act Density 0.009%

    No Known Activations