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

    Neuronpedia

    INDEX
    Explanations

    superlative adjectives describing various qualities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lero
    -0.15
    nze
    -0.15
    øre
    -0.15
    ắt
    -0.15
    adden
    -0.15
    erken
    -0.15
    355
    -0.14
     Exceptions
    -0.14
    mux
    -0.14
    nish
    -0.14
    POSITIVE LOGITS
    /latest
    0.17
    ablish
    0.17
    mas
    0.16
    YPES
    0.16
    IBUTES
    0.15
    IVAL
    0.15
     parte
    0.14
    ylon
    0.14
    -selected
    0.13
    yo
    0.13
    Act Density 0.087%

    No Known Activations