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

    Neuronpedia

    INDEX
    Explanations

    statements indicating belief or disbelief in specific information

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing belief or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ific
    -0.80
    xes
    -0.74
    issance
    -0.69
    quit
    -0.66
    rection
    -0.65
    udo
    -0.63
    Thumbnail
    -0.63
     wast
    -0.62
    backer
    -0.62
    nesses
    -0.62
    POSITIVE LOGITS
    eele
    0.71
     passionately
    0.67
    ASC
    0.64
     Hier
    0.63
    REL
    0.62
    Orig
    0.61
    ================================================================
    0.61
     sincerity
    0.61
     longevity
    0.58
    apesh
    0.58
    Act Density 0.175%

    No Known Activations