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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reaching an outcome or a specific result

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of limitations or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.65
    yi
    -0.60
    sbm
    -0.56
     Bite
    -0.56
    wra
    -0.56
     Surviv
    -0.55
     perf
    -0.55
    tery
    -0.54
     @@
    -0.54
    atech
    -0.54
    POSITIVE LOGITS
     extent
    1.53
    venge
    1.38
     detriment
    1.16
    rouse
    1.09
    livion
    1.02
     lengths
    1.00
     tune
    0.97
     destinations
    0.95
     degree
    0.92
     heights
    0.90
    Act Density 0.437%

    No Known Activations