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

    Neuronpedia

    INDEX
    Explanations

    numerals and their associated contexts within historical or artistic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignon
    -0.15
     Sne
    -0.15
    udas
    -0.14
    orde
    -0.14
    ajs
    -0.14
    loid
    -0.14
    ãĥ¬ãĤ¹
    -0.14
    fieldset
    -0.13
    flix
    -0.13
    enda
    -0.13
    POSITIVE LOGITS
    URITY
    0.15
    Å¡ÃŃ
    0.15
    oped
    0.15
    atrix
    0.14
    combe
    0.14
    fid
    0.14
     coaster
    0.14
     Ramirez
    0.13
     Bust
    0.13
    abet
    0.13
    Act Density 0.012%

    No Known Activations