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

    Neuronpedia

    INDEX
    Explanations

    names containing the substring "jo"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Jo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    binary
    -0.70
    rified
    -0.69
    flies
    -0.68
    cream
    -0.64
    ãĥķãĤ©
    -0.63
    天
    -0.63
     bombard
    -0.63
    nat
    -0.62
    opian
    -0.61
    tle
    -0.61
    POSITIVE LOGITS
    jo
    1.13
    vernment
    1.03
    aquin
    1.02
    unction
    0.92
    zzo
    0.88
    quez
    0.81
    Desk
    0.80
    Jo
    0.80
    atana
    0.79
    zai
    0.78
    Act Density 0.008%

    No Known Activations