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

    Neuronpedia

    INDEX
    Explanations

    mentions of data access

    oai_token-act-pair · gpt-3.5-turbo

    references to data access and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.77
     Herrera
    -0.72
     RELE
    -0.69
    STATE
    -0.65
     Boulevard
    -0.65
    âķ
    -0.62
     Ricardo
    -0.62
     Brush
    -0.60
    áµ
    -0.60
    ª
    -0.59
    POSITIVE LOGITS
    ucks
    1.69
    Dat
    1.22
    ngth
    0.98
    alty
    0.82
    mits
    0.81
    ippers
    0.80
    acters
    0.79
    ensen
    0.77
    onement
    0.76
    ifacts
    0.76
    Act Density 0.001%

    No Known Activations