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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb 'speak' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.87
     Jefus
    -0.85
    [--
    -0.83
     ſche
    -0.82
    waltung
    -0.76
     Etapa
    -0.75
     verily
    -0.73
     Noruega
    -0.73
     Maze
    -0.72
     dommage
    -0.72
    POSITIVE LOGITS
     speak
    2.29
     Speak
    2.13
     speaking
    2.13
     speaks
    2.05
     spoke
    2.02
    Speak
    1.96
     spoken
    1.81
    speak
    1.76
    speaking
    1.73
     Speaking
    1.72
    Act Density 0.037%

    No Known Activations