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

    Neuronpedia

    INDEX
    Explanations

    references to amounts or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    b
    -0.19
    bt
    -0.16
    bdb
    -0.16
    bare
    -0.16
    aiser
    -0.16
    bew
    -0.15
    hta
    -0.15
    boro
    -0.15
    bv
    -0.15
    in
    -0.15
    POSITIVE LOGITS
    fang
    0.25
    gebung
    0.24
    ring
    0.20
    gang
    0.20
    mant
    0.20
    fas
    0.19
    fried
    0.18
    rank
    0.17
    geben
    0.17
    ittel
    0.16
    Act Density 0.005%

    No Known Activations