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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to having various options or resources available for use

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disposal and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hemat
    -0.91
    haw
    -0.75
    sil
    -0.75
    mpeg
    -0.73
    acca
    -0.73
    ovi
    -0.72
    apa
    -0.71
    sky
    -0.71
     Born
    -0.67
    inx
    -0.66
    POSITIVE LOGITS
     disposal
    1.06
    ptions
    0.95
    tainment
    0.89
    ption
    0.86
    bilt
    0.74
    ngth
    0.72
     dispose
    0.72
    ptives
    0.71
    FAULT
    0.71
    brates
    0.70
    Act Density 0.023%

    No Known Activations