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

    Neuronpedia

    INDEX
    Explanations

    technical instructions or coding-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with technical or logistical details and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    less
    -0.67
    ALLY
    -0.63
    ãĥ³
    -0.62
    lessly
    -0.62
    ship
    -0.60
    OV
    -0.60
    ãĥª
    -0.60
    SHIP
    -0.58
    shield
    -0.58
    ctor
    -0.57
    POSITIVE LOGITS
    hips
    1.12
    ystem
    1.10
    cale
    1.09
    pace
    1.08
    hip
    1.08
    pring
    1.07
    paces
    1.05
    heet
    1.04
    ilver
    1.03
    mith
    1.00
    Act Density 0.718%

    No Known Activations