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

    Neuronpedia

    INDEX
    Explanations

    instances where something is captured on video or camera

    oai_token-act-pair · gpt-3.5-turbo

    instances of capturing events or moments on video or camera

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idia
    -0.73
     nomine
    -0.72
     surv
    -0.70
     remedies
    -0.69
    enhagen
    -0.68
     challeng
    -0.68
     goodbye
    -0.67
     ensu
    -0.67
     preservation
    -0.66
     belie
    -0.65
    POSITIVE LOGITS
     Lank
    0.82
    EMOTE
    0.77
    OFF
    0.76
    trap
    0.75
     trap
    0.73
    Cross
    0.72
    tle
    0.70
     traps
    0.69
    Exception
    0.68
     whiff
    0.67
    Act Density 0.110%

    No Known Activations