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

    Neuronpedia

    INDEX
    Explanations

    phrases related to organizations, initiatives, or campaigns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic growth and technology usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caveats
    -0.68
    reenshots
    -0.63
     caveat
    -0.62
    enta
    -0.62
     consolation
    -0.59
    peed
    -0.57
    earchers
    -0.57
    igel
    -0.56
     typo
    -0.55
    pmwiki
    -0.54
    POSITIVE LOGITS
    .�
    0.83
    .''.
    0.72
    .''
    0.69
    ãĢĤ
    0.67
    asca
    0.67
    .</
    0.67
    }.
    0.65
    .","
    0.65
    `.
    0.63
    .'
    0.63
    Act Density 1.704%

    No Known Activations