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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant changes or critical moments

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with critical moments or transitions in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.94
    pload
    -0.85
    uthor
    -0.74
     notor
    -0.74
    unte
    -0.70
    ailability
    -0.69
    krit
    -0.69
    iverpool
    -0.68
    ittle
    -0.68
    osponsors
    -0.67
    POSITIVE LOGITS
    imus
    0.76
    acle
    0.74
    points
    0.72
    ansas
    0.72
    point
    0.70
    ifier
    0.69
    ocrin
    0.67
    forward
    0.67
    ifiers
    0.65
    (){
    0.65
    Act Density 0.038%

    No Known Activations