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

    Neuronpedia

    INDEX
    Explanations

    keywords related to environments or advantageous positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental contexts and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.88
    butt
    -0.84
     actionGroup
    -0.73
    soever
    -0.71
    head
    -0.70
    TPPStreamerBot
    -0.69
    quartered
    -0.69
    dress
    -0.68
    Ô
    -0.67
    Scient
    -0.65
    POSITIVE LOGITS
    isions
    1.17
     env
    1.10
    ENTION
    0.96
    env
    0.90
    urable
    0.85
    igrated
    0.83
    ours
    0.82
    utions
    0.81
    ision
    0.81
    IOR
    0.81
    Act Density 0.008%

    No Known Activations