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

    Neuronpedia

    INDEX
    Explanations

    commands or requests for information

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts for sharing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rane
    -0.75
     ILCS
    -0.74
    urdue
    -0.74
    cdn
    -0.73
    imates
    -0.71
    hered
    -0.66
    rior
    -0.65
    erala
    -0.65
     Antiqu
    -0.63
    Dub
    -0.61
    POSITIVE LOGITS
    tale
    1.46
    ingly
    1.18
    tell
    0.93
     us
    0.77
    ariat
    0.76
     tell
    0.75
     him
    0.74
    roy
    0.72
     me
    0.72
     Tell
    0.71
    Act Density 0.034%

    No Known Activations