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

    Neuronpedia

    INDEX
    Explanations

    phrases related to casual interactions or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to casualness or casual activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    burgh
    -0.86
    CVE
    -0.76
    hner
    -0.73
    asus
    -0.71
    arations
    -0.68
     GOODMAN
    -0.67
    better
    -0.66
    ngth
    -0.65
     Frie
    -0.64
     Luk
    -0.64
    POSITIVE LOGITS
    ization
    0.93
    ties
    0.90
     stroll
    0.84
     casual
    0.84
    ty
    0.81
    ity
    0.80
     minded
    0.78
    isation
    0.77
     observer
    0.77
    ists
    0.76
    Act Density 0.020%

    No Known Activations