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

    Neuronpedia

    INDEX
    Explanations

    professional or academic terms related to education, research, and work

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to societal issues and human experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     injuring
    -0.59
     looph
    -0.56
     suggesting
    -0.56
     noting
    -0.55
     accusing
    -0.54
     Pars
    -0.54
     Palest
    -0.53
     recalling
    -0.52
     highlighting
    -0.52
    icularly
    -0.52
    POSITIVE LOGITS
     reside
    1.18
     prevail
    0.97
     exist
    0.93
     abide
    0.89
     shine
    0.88
     coincide
    0.86
     survive
    0.85
     remain
    0.84
     converge
    0.84
     await
    0.83
    Act Density 0.372%

    No Known Activations