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

    Neuronpedia

    INDEX
    Explanations

    terms related to products or practices being "free" of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of being 'free'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.77
    imura
    -0.77
    UAL
    -0.76
    LER
    -0.76
    older
    -0.73
    IRD
    -0.71
    å¦
    -0.70
     Appears
    -0.69
    attr
    -0.69
    ivic
    -0.69
    POSITIVE LOGITS
    bies
    1.20
    zing
    1.14
    zes
    0.98
    ze
    0.92
    zed
    0.86
    zers
    0.85
    zer
    0.83
     zones
    0.80
    bie
    0.80
    cks
    0.76
    Act Density 0.022%

    No Known Activations