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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs signaling actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.69
     ✭✭
    -0.63
     ")");
    -0.60
    AllowUser
    -0.59
    "]/
    -0.59
    Referanser
    -0.58
     különböz
    -0.58
    FloatField
    -0.57
    Портал
    -0.57
    \"");
    -0.56
    POSITIVE LOGITS
    To
    1.11
     To
    1.10
     Чтобы
    0.92
     Toh
    0.76
     TO
    0.75
    Чтобы
    0.74
     Topeka
    0.67
     לד
    0.67
     للاسماء
    0.65
     Whom
    0.65
    Act Density 0.130%

    No Known Activations