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

    Neuronpedia

    INDEX
    Explanations

    information related to announcements and official communications

    oai_token-act-pair · gpt-3.5-turbo

    announcements or formal declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shrugged
    -0.76
    umably
    -0.68
     reused
    -0.64
    lier
    -0.62
     undercut
    -0.60
    hatt
    -0.59
    toggle
    -0.58
    iddling
    -0.58
     shrug
    -0.58
     blamed
    -0.58
    POSITIVE LOGITS
     tonight
    0.87
     yourselves
    0.85
     hereby
    0.83
     hereafter
    0.81
     Patreon
    0.80
     PLEASE
    0.78
     my
    0.77
     OUR
    0.76
     ONLY
    0.76
     YOUR
    0.76
    Act Density 1.539%

    No Known Activations