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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "behind."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilded
    -0.15
    sett
    -0.15
    idge
    -0.14
    ty
    -0.14
    -strokes
    -0.14
    ÏĦον
    -0.14
    eros
    -0.14
    yp
    -0.14
     imped
    -0.13
    cakes
    -0.13
    POSITIVE LOGITS
    /in
    0.18
    -the
    0.17
    aler
    0.16
     behind
    0.15
    ness
    0.15
    s
    0.15
    wards
    0.15
     cre
    0.14
     Tough
    0.14
     Behind
    0.14
    Act Density 0.024%

    No Known Activations