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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "fro."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ariat
    -0.17
    ouve
    -0.16
    rong
    -0.16
    paren
    -0.16
    rq
    -0.16
    ÑĥÑģк
    -0.16
    chaft
    -0.16
    OUCH
    -0.15
    rust
    -0.15
    raya
    -0.15
    POSITIVE LOGITS
    sted
    0.37
    lick
    0.35
    thy
    0.33
    lic
    0.32
    thing
    0.29
    sts
    0.27
    zens
    0.25
    licing
    0.25
    thed
    0.25
    th
    0.23
    Act Density 0.007%

    No Known Activations