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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to disassembly and maintenance

    oai_token-act-pair · gpt-3.5-turbo

    references to unscheduled events and precarious situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heartbeat
    -0.70
    hart
    -0.64
    burn
    -0.61
     cardio
    -0.61
    bread
    -0.61
     Leia
    -0.61
     authent
    -0.60
     crypt
    -0.59
     Benedict
    -0.59
     Celt
    -0.58
    POSITIVE LOGITS
    rupulous
    1.06
    ategory
    1.06
     unsc
    0.84
    ©¶æ
    0.84
    ansky
    0.82
    prising
    0.81
    apers
    0.79
    BLIC
    0.77
     advant
    0.76
    ĵĺ
    0.76
    Act Density 0.027%

    No Known Activations