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

    Neuronpedia

    INDEX
    Explanations

    currency symbols and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whatever
    -0.55
    whatever
    -0.49
    Whatever
    -0.47
     Whatever
    -0.46
     whichever
    -0.26
     whoever
    -0.19
    atever
    -0.19
    ìĺģ
    -0.16
     wherever
    -0.16
    ĨĴ
    -0.16
    POSITIVE LOGITS
    104
    0.32
    110
    0.31
    105
    0.31
    102
    0.31
    101
    0.31
    103
    0.31
    107
    0.30
    113
    0.30
    106
    0.29
    109
    0.29
    Act Density 0.122%

    No Known Activations