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

    Neuronpedia

    INDEX
    Explanations

    references to academic or formal studying activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "studying" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    por
    -0.75
    shr
    -0.70
    PRESS
    -0.68
    cakes
    -0.66
    cycl
    -0.63
    Anth
    -0.62
    trap
    -0.60
    responsive
    -0.59
    theless
    -0.58
     catast
    -0.58
    POSITIVE LOGITS
     abroad
    0.83
     studying
    0.81
    udo
    0.81
    arios
    0.81
    study
    0.79
    uto
    0.73
     study
    0.73
    umat
    0.73
    izabeth
    0.73
    essors
    0.72
    Act Density 0.027%

    No Known Activations