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

    Neuronpedia

    INDEX
    Explanations

    character sequences or patterns within data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    JNIEnv
    -0.49
    ActionMode
    -0.48
     operators
    -0.46
    setopt
    -0.45
    partimento
    -0.42
     qu
    -0.41
    ,
    -0.41
     OR
    -0.39
     House
    -0.38
     lahat
    -0.38
    POSITIVE LOGITS
    HasBeenSet
    0.88
     Réponses
    0.87
     مشين
    0.85
    SharedCtor
    0.82
     Савезне
    0.77
    `,
    0.74
    0.74
     Puls
    0.74
     Suf
    0.73
     للمعارف
    0.73
    Act Density 0.027%

    No Known Activations