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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain numerical references or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iku
    -0.16
    olina
    -0.15
    tiny
    -0.15
    erm
    -0.15
    票
    -0.14
    zs
    -0.14
    locks
    -0.14
     Pavel
    -0.13
    aland
    -0.13
    uteÄį
    -0.13
    POSITIVE LOGITS
    arl
    0.16
    OPY
    0.15
    REDIENT
    0.14
    maf
    0.13
    StackSize
    0.13
    _hat
    0.13
    fold
    0.13
    734
    0.13
    aga
    0.13
    akin
    0.13
    Act Density 0.228%

    No Known Activations