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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or change

    oai_token-act-pair · gpt-3.5-turbo

    dynamic verbs and adjectives describing movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chery
    -0.96
    hers
    -0.83
    oot
    -0.82
    TRY
    -0.80
    saf
    -0.79
    chie
    -0.78
    notice
    -0.78
    ère
    -0.77
    thodox
    -0.77
    ses
    -0.76
    POSITIVE LOGITS
     sands
    0.86
     tides
    0.85
     Archdemon
    0.84
     tide
    0.79
     rain
    0.78
     sickness
    0.76
     debris
    0.75
     footsteps
    0.75
     sun
    0.74
     Sands
    0.73
    Act Density 0.184%

    No Known Activations