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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    references to nationalities or affiliations of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     safely
    -0.73
    eanor
    -0.73
    jriwal
    -0.73
    anwhile
    -0.72
     belie
    -0.66
     vibe
    -0.65
     downgrade
    -0.63
     balance
    -0.63
    ignty
    -0.62
     job
    -0.62
    POSITIVE LOGITS
     Thom
    0.76
     architects
    0.69
     Architects
    0.66
     Interactive
    0.66
     Ink
    0.63
    Begin
    0.62
     Editors
    0.61
    ographers
    0.60
    ateurs
    0.60
    ãĤ¢ãĥ«
    0.59
    Act Density 0.436%

    No Known Activations