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

    Neuronpedia

    INDEX
    Explanations

    words starting with "host" or typos of "host"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ost."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.82
    xon
    -0.70
    ggies
    -0.67
     Quinn
    -0.66
     Berk
    -0.66
    gging
    -0.66
    ptive
    -0.65
    isters
    -0.65
    ught
    -0.65
     Ventura
    -0.63
    POSITIVE LOGITS
    algia
    1.21
    ost
    1.11
    een
    1.08
    rand
    1.06
    rophic
    1.01
    eering
    1.01
    ensibly
    0.98
    ricting
    0.98
    alg
    0.96
    rophe
    0.96
    Act Density 0.016%

    No Known Activations