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

    Neuronpedia

    INDEX
    Explanations

    social media-related actions such as 'shared', 'viewed', 'edited' or similar phrases

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to sharing, viewing, and testing information or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lication
    -0.63
    ears
    -0.61
     Latter
    -0.58
    Zone
    -0.57
    rouse
    -0.56
     Cong
    -0.56
    ctive
    -0.56
    article
    -0.55
    comes
    -0.54
    vice
    -0.54
    POSITIVE LOGITS
     since
    0.90
     repeatedly
    0.82
     lately
    0.82
     by
    0.79
     numerous
    0.78
     unanimously
    0.78
     elsewhere
    0.76
     countless
    0.75
     extensively
    0.75
     successfully
    0.72
    Act Density 0.183%

    No Known Activations