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

    Neuronpedia

    INDEX
    Explanations

    words related to negative emotions like hatred and distrust

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    aqu
    -0.64
    inventoryQuantity
    -0.59
    annis
    -0.55
    pletion
    -0.55
    umm
    -0.55
    orage
    -0.54
     helicop
    -0.54
     Horizon
    -0.54
    atonin
    -0.54
    changes
    -0.52
    POSITIVE LOGITS
     hated
    0.66
    lessly
    0.65
     hatred
    0.62
     toward
    0.61
     prejudice
    0.61
     vengeance
    0.61
    ãĥĨ
    0.61
     towards
    0.60
    ¿½
    0.58
    fully
    0.58
    Act Density 8.367%

    No Known Activations