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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases indicating contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    سطس
    -0.66
    anskje
    -0.59
    ñones
    -0.59
     referenties
    -0.57
    slee
    -0.57
    Mete
    -0.55
    }=[
    -0.54
     selanjutnya
    -0.54
    swal
    -0.54
     makl
    -0.53
    POSITIVE LOGITS
     reverses
    1.11
     Reverse
    1.05
     reverse
    1.03
     inversion
    1.02
     opposes
    1.01
     Opposite
    1.00
    逆
    0.99
     reversal
    0.97
     Inverse
    0.97
     inver
    0.96
    Act Density 0.242%

    No Known Activations