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

    Neuronpedia

    INDEX
    Explanations

    phrases related to habits or repeated actions

    oai_token-act-pair · gpt-3.5-turbo

    references to patterns of behavior or actions that are repeated regularly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.90
     SAR
    -0.84
    ammy
    -0.82
     RIS
    -0.75
    cross
    -0.74
    ndum
    -0.66
     GOODMAN
    -0.66
    ILLE
    -0.65
    headers
    -0.65
    anmar
    -0.65
    POSITIVE LOGITS
     habit
    1.21
    uated
    1.14
    ually
    1.08
    uate
    1.05
     habits
    1.04
    uation
    1.04
    uates
    0.94
    uating
    0.85
    uously
    0.74
    uous
    0.74
    Act Density 0.006%

    No Known Activations