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

    Neuronpedia

    INDEX
    Explanations

    terms related to web redirects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Newman
    -0.66
     lights
    -0.62
    serv
    -0.59
    sw
    -0.59
    phant
    -0.57
    wake
    -0.56
     fre
    -0.54
    ples
    -0.54
     Rudd
    -0.52
     Tw
    -0.52
    POSITIVE LOGITS
    ometimes
    0.94
    omething
    0.90
    hift
    0.86
    anamo
    0.82
    imentary
    0.81
    Downloadha
    0.80
    hirt
    0.78
    olate
    0.78
    ilver
    0.76
    heet
    0.74
    Act Density 0.115%

    No Known Activations