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

    Neuronpedia

    INDEX
    Explanations

    expressions of negativity or discontent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    awful followed by negative descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.73
     TestBed
    -0.61
     سكانية
    -0.60
    batore
    -0.56
    imei
    -0.55
     Peres
    -0.55
    TCL
    -0.53
    geren
    -0.52
    itere
    -0.52
    ieniem
    -0.52
    POSITIVE LOGITS
     awful
    1.13
    awful
    1.09
    Awful
    0.94
     awfully
    0.67
     Aw
    0.60
    Aw
    0.54
     horrid
    0.52
     awk
    0.49
     dreadful
    0.48
     aw
    0.47
    Act Density 0.002%

    No Known Activations