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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to taking or making changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ione
    -0.16
    (chr
    -0.14
     comb
    -0.14
    436
    -0.14
    ikan
    -0.14
    iton
    -0.14
    iju
    -0.14
     Gig
    -0.13
    aket
    -0.13
    ion
    -0.13
    POSITIVE LOGITS
    .IsNull
    0.15
    宾
    0.14
    -roll
    0.14
     itir
    0.13
     αÏĥ
    0.13
     GRAT
    0.13
    inox
    0.13
    oyer
    0.13
    å¿į
    0.13
     Gros
    0.13
    Act Density 0.289%

    No Known Activations