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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that signify evaluations or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensch
    -0.16
     Shaft
    -0.15
    abeth
    -0.15
    qa
    -0.15
     Mell
    -0.15
    nect
    -0.14
    erno
    -0.14
    posite
    -0.14
    ist
    -0.14
     I
    -0.14
    POSITIVE LOGITS
    _Lean
    0.17
    ewis
    0.16
    LEAN
    0.15
     ActionTypes
    0.15
    borg
    0.15
    chwitz
    0.14
    اخر
    0.14
    ÑĦÑĤ
    0.14
    aille
    0.14
     поба
    0.14
    Act Density 0.002%

    No Known Activations