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

    Neuronpedia

    INDEX
    Explanations

    the act of speech or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [--
    -0.86
     Jefus
    -0.86
    tagHelperRunner
    -0.82
     ſche
    -0.74
    bbene
    -0.74
     verily
    -0.72
    Guys
    -0.71
    ſelves
    -0.70
    waltung
    -0.70
     Deutschlands
    -0.70
    POSITIVE LOGITS
     speak
    2.99
     speaking
    2.98
     Speak
    2.73
     speaks
    2.63
     spoke
    2.63
    Speak
    2.56
    speaking
    2.47
     Speaking
    2.44
     spoken
    2.39
    speak
    2.37
    Act Density 0.060%

    No Known Activations