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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing dissatisfaction or strong emotion about a specific situation

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing disappointment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.72
    iHUD
    -0.67
    orage
    -0.66
    ailability
    -0.64
    kamp
    -0.64
    zman
    -0.64
     pione
    -0.62
    ãĥ¼ãĤ¯
    -0.61
     fide
    -0.61
    ead
    -0.61
    POSITIVE LOGITS
    soever
    0.70
     they
    0.69
    chers
    0.68
     exists
    0.67
     someone
    0.67
    someone
    0.67
     nobody
    0.66
     we
    0.66
     arose
    0.65
     despite
    0.64
    Act Density 0.099%

    No Known Activations