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

    Neuronpedia

    INDEX
    Explanations

    queries pertaining to technical instructions or feedback

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence structure cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.83
     neighb
    -0.82
     prosec
    -0.80
     polic
    -0.80
     brist
    -0.79
     skelet
    -0.78
     cler
    -0.77
     uranium
    -0.77
     tram
    -0.76
     dermat
    -0.75
    POSITIVE LOGITS
    Firstly
    2.07
    First
    1.79
    Anyway
    1.77
    Below
    1.76
    Before
    1.76
    Here
    1.75
    Unfortunately
    1.74
    Let
    1.74
    Basically
    1.71
    Advertisements
    1.71
    Act Density 0.428%

    No Known Activations