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

    Neuronpedia

    INDEX
    Explanations

    frequent occurrences of the word "ach" along with terms related to decision-making, endings, and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhan
    -0.14
    FE
    -0.14
    HO
    -0.14
     Hanson
    -0.14
     Gul
    -0.14
    λον
    -0.14
    orthy
    -0.13
     Pra
    -0.13
    551
    -0.13
    anco
    -0.13
    POSITIVE LOGITS
    amic
    0.17
    -by
    0.17
    amet
    0.17
    _ber
    0.16
    adic
    0.16
     Carlson
    0.16
    _bm
    0.15
    è³¢
    0.15
     Bell
    0.15
    bell
    0.15
    Act Density 0.040%

    No Known Activations