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

    Neuronpedia

    INDEX
    Explanations

    Swedish words with specific characters like "å" and "ö"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific symbols or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kernels
    -0.70
    ipop
    -0.70
    idepress
    -0.69
    IFIED
    -0.67
    aneously
    -0.67
    iates
    -0.67
    icity
    -0.67
     overdoses
    -0.67
    iazep
    -0.66
    iate
    -0.65
    POSITIVE LOGITS
    OOL
    0.83
    å
    0.82
    hl
    0.81
    ¯
    0.81
    ð
    0.79
    rd
    0.79
    rn
    0.79
    sb
    0.79
    ¢
    0.77
    µ
    0.77
    Act Density 0.027%

    No Known Activations