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

    Neuronpedia

    INDEX
    Explanations

    keywords related to a specific character or theme, possibly from a comic book or related content

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fishing and enzymes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hya
    -0.76
    arest
    -0.76
    apest
    -0.74
    atari
    -0.72
    elcome
    -0.71
    erest
    -0.71
    ouls
    -0.71
    ÅĤ
    -0.69
    hum
    -0.68
    ental
    -0.66
    POSITIVE LOGITS
    sonian
    0.95
     inhibitor
    0.79
    ctl
    0.78
    ¯¯¯¯
    0.77
    TAIN
    0.77
    llan
    0.76
     enzyme
    0.75
     obser
    0.74
     nomine
    0.73
    ¯¯
    0.72
    Act Density 0.017%

    No Known Activations