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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "char."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eh
    -0.18
    ea
    -0.17
    enia
    -0.16
    y
    -0.16
    chants
    -0.16
    amiento
    -0.15
    yn
    -0.15
    yon
    -0.15
    elyn
    -0.15
    egan
    -0.14
    POSITIVE LOGITS
    tered
    0.31
    coal
    0.29
    ismatic
    0.29
    itable
    0.27
    itably
    0.26
    isma
    0.24
    akter
    0.23
    lotte
    0.22
    izard
    0.22
    leston
    0.21
    Act Density 0.012%

    No Known Activations