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

    Neuronpedia

    INDEX
    Explanations

    structured sentences and phrases with specific kinds of punctuation marks, like quotes, commas, and periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     throats
    -0.58
    ngth
    -0.57
     sketches
    -0.54
     Reporting
    -0.54
     drawings
    -0.53
     bombard
    -0.53
     magazines
    -0.53
     Gork
    -0.51
     pores
    -0.51
     Moose
    -0.49
    POSITIVE LOGITS
     feasible
    0.83
     incent
    0.81
     deterrent
    0.80
    soType
    0.80
     incentiv
    0.78
     counterproductive
    0.77
     hypocritical
    0.74
     preferable
    0.73
     justified
    0.72
     mutually
    0.72
    Act Density 0.522%

    No Known Activations