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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to science and technology

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to technology and scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.80
    ABLE
    -0.72
    Tur
    -0.71
    yss
    -0.70
    Shock
    -0.69
    Honest
    -0.66
    $.
    -0.66
    Miami
    -0.65
    ARR
    -0.65
    Ton
    -0.62
    POSITIVE LOGITS
    hip
    1.10
    hips
    1.08
    afety
    1.07
    paces
    1.05
    poons
    1.01
    mith
    0.97
    ystem
    0.95
    chool
    0.93
    etter
    0.92
    etting
    0.92
    Act Density 0.501%

    No Known Activations