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

    Neuronpedia

    INDEX
    Explanations

    key concepts and terms related to identification and evaluation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Enumeration
    -0.15
    bert
    -0.15
    croft
    -0.14
     ngang
    -0.14
     Mirror
    -0.14
     #__
    -0.14
     Skeleton
    -0.14
     skeleton
    -0.13
     Hoy
    -0.13
    /conf
    -0.13
    POSITIVE LOGITS
    riger
    0.16
    ooks
    0.16
    alis
    0.15
    Ïĥε
    0.15
    esty
    0.15
    umph
    0.15
    ewater
    0.15
    ystore
    0.15
    ouse
    0.14
    sip
    0.14
    Act Density 0.001%

    No Known Activations