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

    Neuronpedia

    INDEX
    Explanations

    phrases related to readers and audience interaction

    oai_token-act-pair · gpt-3.5-turbo

    references to readers and their engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reloaded
    -0.75
    --+
    -0.68
     restart
    -0.65
    ¬¼
    -0.63
     Skull
    -0.60
     drums
    -0.60
     halftime
    -0.60
    ayne
    -0.59
    senal
    -0.58
     Winning
    -0.58
    POSITIVE LOGITS
    hip
    1.94
    hips
    1.25
    uggest
    1.13
    itarian
    0.88
    bridge
    0.85
    boy
    0.85
    erv
    0.84
    20439
    0.84
    iences
    0.82
    icles
    0.79
    Act Density 0.047%

    No Known Activations