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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or functions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bliž
    -0.52
     postIndex
    -0.51
     surfaces
    -0.51
     <<<<<<<<<<<<<<
    -0.51
    خوری
    -0.51
    셋
    -0.50
     GenerationType
    -0.49
     pe
    -0.48
    omyces
    -0.48
    ر
    -0.47
    POSITIVE LOGITS
     plays
    1.97
     Plays
    1.85
    Plays
    1.66
    plays
    1.54
     spielt
    0.87
     trades
    0.83
     dramas
    0.80
     Normdatei
    0.80
    parsedMessage
    0.79
    Activités
    0.78
    Act Density 0.172%

    No Known Activations