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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain frequency modifiers related to expectations or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cause
    -0.80
    icity
    -0.74
    itional
    -0.73
    ission
    -0.73
    utterstock
    -0.72
    iken
    -0.71
    yson
    -0.71
    zbollah
    -0.69
    iece
    -0.66
    ogram
    -0.65
    POSITIVE LOGITS
     someone
    0.89
     understatement
    0.88
     such
    0.86
     seasoned
    0.85
     outsiders
    0.84
     inexperienced
    0.75
     modern
    0.74
     reputable
    0.74
     any
    0.72
     rookies
    0.72
    Act Density 0.324%

    No Known Activations