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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinion pieces (op-eds) in newspapers or articles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "op-ed" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶ħ
    -0.84
    wagen
    -0.77
     Galileo
    -0.74
    ILLE
    -0.73
    esome
    -0.69
     Suc
    -0.69
    ãĤ£
    -0.68
    åŃIJ
    -0.67
    auga
    -0.66
    VILLE
    -0.65
    POSITIVE LOGITS
    osite
    1.04
    iates
    1.03
    onent
    1.01
    orter
    0.95
     op
    0.91
    yright
    0.90
    inion
    0.89
    aqu
    0.89
    iate
    0.88
    rog
    0.86
    Act Density 0.005%

    No Known Activations