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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific characters or people within a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    references to characters or subjects in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.81
    Bloomberg
    -0.79
    ancial
    -0.78
    Share
    -0.77
    ional
    -0.77
    thood
    -0.75
    IFA
    -0.72
    hips
    -0.71
    iliate
    -0.70
    iversity
    -0.69
    POSITIVE LOGITS
     door
    1.09
     darkness
    1.05
     girl
    1.02
     waiter
    1.00
     doorway
    1.00
     brun
    1.00
     blonde
    0.99
     slightest
    0.99
     remainder
    0.98
     waitress
    0.95
    Act Density 0.362%

    No Known Activations