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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edy
    -0.17
    antha
    -0.16
    ustos
    -0.15
    chter
    -0.14
    edian
    -0.14
    redient
    -0.14
    tower
    -0.13
    redients
    -0.13
    _HIT
    -0.13
    /of
    -0.13
    POSITIVE LOGITS
    ensively
    0.16
    815
    0.16
    .integration
    0.14
     Bag
    0.14
     breadcrumb
    0.14
    _integration
    0.14
    _bag
    0.14
     sac
    0.13
    ìĥģìľĦ
    0.13
    707
    0.13
    Act Density 0.012%

    No Known Activations