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

    Neuronpedia

    INDEX
    Explanations

    specific chemical compounds or elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemical compounds and scientific terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guid
    -0.68
     Cir
    -0.65
     lin
    -0.63
     Hacker
    -0.62
    DOC
    -0.59
     bunk
    -0.58
    SIGN
    -0.57
     tooth
    -0.57
     Line
    -0.57
     whis
    -0.57
    POSITIVE LOGITS
    rily
    0.77
    mentioned
    0.75
    theless
    0.74
    /-
    0.73
    selves
    0.72
    uably
    0.71
    then
    0.71
    ndra
    0.70
    ilk
    0.70
    icably
    0.69
    Act Density 0.290%

    No Known Activations