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

    Neuronpedia

    INDEX
    Explanations

    the term "X-Men"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     forgiven
    -0.66
     writ
    -0.61
     starters
    -0.60
     starting
    -0.60
     establishment
    -0.58
     TODAY
    -0.58
     scoff
    -0.58
     keeping
    -0.58
     AVG
    -0.58
     reve
    -0.57
    POSITIVE LOGITS
    avier
    1.20
    anth
    1.15
    posed
    1.14
    mas
    1.13
    OX
    1.08
    peria
    1.06
    yz
    1.06
    XXXX
    1.05
    BOX
    1.05
    posure
    1.04
    Act Density 0.029%

    No Known Activations