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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and statements about authorship and differing viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate authorship and the expression of personal opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    multipl
    -0.74
    chio
    -0.70
    Reloaded
    -0.69
     Furious
    -0.69
    Mot
    -0.68
    trap
    -0.68
    Frag
    -0.67
    externalActionCode
    -0.63
    delay
    -0.62
    Finish
    -0.61
    POSITIVE LOGITS
     editorial
    0.91
     affiliate
    0.81
     opinions
    0.75
     Editorial
    0.73
    hani
    0.73
     copyright
    0.72
     authors
    0.72
    ravis
    0.71
     author
    0.71
     copyrighted
    0.71
    Act Density 0.201%

    No Known Activations