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

    Neuronpedia

    INDEX
    Explanations

    interactions involving communication and requests for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wikipedia
    -0.74
    hemy
    -0.67
     Inher
    -0.64
    rawdownloadcloneembedreportprint
    -0.64
    gur
    -0.63
     floats
    -0.63
    utenberg
    -0.62
    Wikipedia
    -0.61
     dominates
    -0.61
    ibles
    -0.60
    POSITIVE LOGITS
     requesting
    1.11
     inquire
    0.97
     asking
    0.94
     hotline
    0.90
     informing
    0.90
     inquiries
    0.89
     voic
    0.89
     enqu
    0.89
     urgently
    0.88
     fax
    0.88
    Act Density 0.163%

    No Known Activations