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

    Neuronpedia

    INDEX
    Explanations

    phrases related to online activities or technologies

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to competitive events or conditions involving risk and caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.74
    33
    -0.73
    man
    -0.69
    guy
    -0.68
    43
    -0.67
     Defendant
    -0.67
    face
    -0.67
     complying
    -0.66
     man
    -0.66
    uer
    -0.65
    POSITIVE LOGITS
    EStreamFrame
    0.89
    orbit
    0.83
    anamo
    0.81
    RGB
    0.80
    localhost
    0.78
    EngineDebug
    0.73
    OVA
    0.72
    âķIJ
    0.71
    acet
    0.70
    aris
    0.70
    Act Density 0.454%

    No Known Activations