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

    Neuronpedia

    INDEX
    Explanations

    phrases related to names or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.63
    enei
    -0.62
    dal
    -0.60
    aly
    -0.58
    orts
    -0.57
     DSL
    -0.56
    eks
    -0.56
    essel
    -0.55
    .:
    -0.54
    .):
    -0.54
    POSITIVE LOGITS
    whose
    1.32
    which
    1.19
    along
    1.00
     nicknamed
    0.99
    who
    0.97
    including
    0.96
     dubbed
    0.95
    named
    0.93
    particularly
    0.91
    pictured
    0.91
    Act Density 0.141%

    No Known Activations