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

    Neuronpedia

    INDEX
    Explanations

    information related to reasoning and argumentation

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical values or statistics related to critical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Custom
    -0.64
     Instr
    -0.63
     handshake
    -0.63
     "+
    -0.63
     \"
    -0.63
     Likes
    -0.62
     swearing
    -0.61
     Guinness
    -0.61
     slang
    -0.60
     "-
    -0.60
    POSITIVE LOGITS
     underscores
    0.92
     illuminating
    0.92
     empir
    0.90
     underscore
    0.87
     empirical
    0.87
     miscon
    0.86
     illuminate
    0.83
    orthy
    0.83
     undersc
    0.82
     troubling
    0.82
    Act Density 0.620%

    No Known Activations