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

    Neuronpedia

    INDEX
    Explanations

    concepts related to theoretical frameworks and idealizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antaine
    -0.61
     nece
    -0.56
    AndEndTag
    -0.55
     neceff
    -0.55
     TextAlign
    -0.54
    tagHelperRunner
    -0.54
     erle
    -0.54
     stubble
    -0.53
    bunda
    -0.52
    Acerca
    -0.52
    POSITIVE LOGITS
     but
    0.66
     theoretically
    0.65
     promise
    0.64
     ideal
    0.64
     idealistic
    0.62
     theoretical
    0.61
     teórico
    0.60
     promises
    0.60
    lof
    0.59
     dream
    0.58
    Act Density 0.557%

    No Known Activations