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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "char" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.18
    yn
    -0.18
    yny
    -0.17
    el
    -0.16
    eh
    -0.16
    etas
    -0.16
    amiento
    -0.16
    ea
    -0.15
    grad
    -0.15
    ese
    -0.15
    POSITIVE LOGITS
    ismatic
    0.28
    coal
    0.26
    akter
    0.26
    isma
    0.24
    itably
    0.24
    tered
    0.23
    itable
    0.23
    acters
    0.20
    leston
    0.19
    lene
    0.19
    Act Density 0.014%

    No Known Activations