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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions and states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.54
     Normdatei
    -0.47
     Hoffman
    -0.45
    MigrationBuilder
    -0.43
    unhofer
    -0.42
     åt
    -0.42
    blis
    -0.41
    anyahu
    -0.41
    橙
    -0.41
    エット
    -0.41
    POSITIVE LOGITS
     beating
    1.95
     beaten
    1.84
     beat
    1.62
     beats
    1.50
     Beat
    1.41
    beaten
    1.37
     BEAT
    1.37
    Beat
    1.36
     geschlagen
    1.35
    beat
    1.30
    Act Density 0.430%

    No Known Activations