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

    Neuronpedia

    INDEX
    Explanations

    words related to excitement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "re" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rabb
    -0.74
    ividual
    -0.66
    ãħĭ
    -0.66
    olesterol
    -0.63
    avorite
    -0.63
    ertodd
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.61
    circ
    -0.61
    oice
    -0.61
    vertisement
    -0.60
    POSITIVE LOGITS
    bral
    1.08
    cks
    1.07
    cht
    1.07
    zza
    1.00
    ngth
    0.96
    xit
    0.95
    porter
    0.94
    gger
    0.91
    versible
    0.90
    uther
    0.88
    Act Density 0.033%

    No Known Activations