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

    Neuronpedia

    INDEX
    Explanations

    concepts related to probability and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wyn
    -0.15
    ensis
    -0.15
    à¹Ħว
    -0.14
    åĦĢ
    -0.14
     Sala
    -0.14
    icz
    -0.13
    apiro
    -0.13
     Vaults
    -0.13
    illard
    -0.13
     olmaz
    -0.13
    POSITIVE LOGITS
    pline
    0.15
    odb
    0.15
    uality
    0.15
    ibus
    0.15
    füg
    0.14
    igers
    0.14
    atform
    0.14
    erva
    0.14
    Ùį
    0.14
    unal
    0.13
    Act Density 0.106%

    No Known Activations