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

    Neuronpedia

    INDEX
    Explanations

    editor's notes within text

    oai_token-act-pair · gpt-3.5-turbo

    references to editorial notes or annotations within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrim
    -0.59
     stret
    -0.58
    ãĥ¼ãĥĨãĤ£
    -0.57
     manif
    -0.56
    milo
    -0.55
     isolation
    -0.54
    stood
    -0.54
     vain
    -0.54
    é¾
    -0.53
    cular
    -0.53
    POSITIVE LOGITS
    *:
    0.97
    :
    0.95
    .:
    0.87
    *)
    0.86
     EDIT
    0.84
    :]
    0.80
    !:
    0.80
    ":"","
    0.79
    ::
    0.79
     NOTE
    0.78
    Act Density 0.050%

    No Known Activations