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

    Neuronpedia

    INDEX
    Explanations

    words related to physical strain or tension

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structural constraints or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.83
    merce
    -0.83
    STON
    -0.82
     Dragonbound
    -0.76
    culosis
    -0.69
    SHIP
    -0.68
    wolves
    -0.65
    HCR
    -0.64
    IAS
    -0.63
    bear
    -0.62
    POSITIVE LOGITS
    angle
    1.22
    angled
    1.19
    angling
    1.14
    agg
    1.03
    aining
    1.00
    aint
    0.98
    atum
    0.97
    ainer
    0.95
    ained
    0.95
    inger
    0.95
    Act Density 0.008%

    No Known Activations