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

    Neuronpedia

    INDEX
    Explanations

    locations or environments

    oai_token-act-pair · gpt-3.5-turbo

    references to critical issues and conditions in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mone
    -0.63
     guiActiveUn
    -0.60
     "$:/
    -0.60
    ãĥ£
    -0.58
    ãĥ¥
    -0.55
    ãĤ¸
    -0.53
    cam
    -0.53
    ably
    -0.52
     veto
    -0.52
    oug
    -0.52
    POSITIVE LOGITS
     nonetheless
    0.75
    .
    0.71
     anyway
    0.70
    awaru
    0.67
     wherever
    0.66
     everywhere
    0.63
     overwhelmed
    0.63
    —
    0.63
    ."[
    0.62
    .[
    0.61
    Act Density 1.193%

    No Known Activations