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

    Neuronpedia

    INDEX
    Explanations

    verbs related to revealing, uncovering, or disclosing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ovich
    -0.65
    pace
    -0.61
    ovic
    -0.61
    imus
    -0.61
    é¾įå
    -0.60
    istically
    -0.60
    oran
    -0.59
    owicz
    -0.58
    anian
    -0.56
     amen
    -0.55
    POSITIVE LOGITS
    lling
    2.03
    llers
    1.92
    lled
    1.76
    ller
    1.65
    rence
    1.35
    xual
    1.26
    rent
    1.24
    lly
    1.19
    illance
    1.16
    rers
    1.15
    Act Density 0.080%

    No Known Activations