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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time passing or actions being done repeatedly

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stay
    -0.61
    ãĥĩ
    -0.58
     relates
    -0.58
    onnaissance
    -0.57
     traged
    -0.56
     omit
    -0.56
     Photographer
    -0.55
    iere
    -0.54
    mist
    -0.54
     Cabin
    -0.54
    POSITIVE LOGITS
     ready
    1.23
     done
    1.14
     finished
    1.10
     gone
    1.08
     satisfied
    1.04
     exhausted
    1.00
     sufficiently
    0.90
     halfway
    0.89
     convinced
    0.86
     bored
    0.85
    Act Density 0.165%

    No Known Activations