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

    Neuronpedia

    INDEX
    Explanations

    the word "tent" at varying levels of strength

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    course
    -0.65
    ÃĽ
    -0.64
    Course
    -0.63
     Emin
    -0.63
     beet
    -0.62
     Uz
    -0.60
     caut
    -0.60
     symmetry
    -0.60
     Cuomo
    -0.59
     fats
    -0.59
    POSITIVE LOGITS
    acle
    1.49
    atively
    1.41
    pole
    1.34
    acles
    1.16
    acular
    1.14
     encamp
    0.97
    acly
    0.96
     poles
    0.94
    pipe
    0.89
     pole
    0.87
    Act Density 0.047%

    No Known Activations