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

    Neuronpedia

    INDEX
    Explanations

    instances of "applies to" statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express applicability or relevance to specific subjects or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erd
    -0.80
    iev
    -0.76
    achev
    -0.73
    icter
    -0.72
    urat
    -0.67
    arov
    -0.67
    itchie
    -0.66
    riber
    -0.66
    Champ
    -0.66
    ileaks
    -0.66
    POSITIVE LOGITS
     ALL
    0.94
     EVERY
    0.91
     all
    0.86
     everyone
    0.86
     everything
    0.84
     every
    0.84
     everybody
    0.83
     ours
    0.76
    etheless
    0.74
     both
    0.74
    Act Density 0.341%

    No Known Activations