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

    Neuronpedia

    INDEX
    Explanations

    terms related to names and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĪка
    -0.17
    cel
    -0.15
    VML
    -0.15
    stag
    -0.15
    OTT
    -0.15
    ixmap
    -0.14
    erialize
    -0.14
    lew
    -0.14
    urette
    -0.14
    ategory
    -0.14
    POSITIVE LOGITS
     Sw
    0.25
    stakes
    0.24
    peare
    0.19
    (sw
    0.18
     sw
    0.18
    /sw
    0.18
    Sw
    0.17
    erve
    0.16
    urai
    0.16
    iji
    0.16
    Act Density 0.032%

    No Known Activations