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

    Neuronpedia

    INDEX
    Explanations

    adverbs that indicate certainty or degree of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.83
     Persia
    -0.81
     ſtate
    -0.79
    fjspx
    -0.77
     raiſ
    -0.75
     betweenstory
    -0.75
     vectra
    -0.74
     AssemblyTitle
    -0.74
     pleaſure
    -0.74
     myſelf
    -0.73
    POSITIVE LOGITS
     being
    0.87
     is
    0.84
     also
    0.78
     be
    0.77
     becoming
    0.75
     a
    0.72
     was
    0.70
     être
    0.69
     è
    0.68
     going
    0.68
    Act Density 0.324%

    No Known Activations