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

    Neuronpedia

    INDEX
    Explanations

    comments or discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to comments or commentary in a discussion context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Recon
    -0.75
    ccording
    -0.69
    red
    -0.68
     abduction
    -0.65
    isen
    -0.65
     Sinai
    -0.65
    ça
    -0.65
    icz
    -0.64
     Starr
    -0.63
    owship
    -0.63
    POSITIVE LOGITS
    comments
    0.92
     comments
    0.89
     Comments
    0.84
     comment
    0.81
    ature
    0.81
    ariat
    0.78
     commenters
    0.78
     threads
    0.77
     sections
    0.77
    atures
    0.77
    Act Density 0.032%

    No Known Activations