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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "certain"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "certain."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cum
    -0.71
    TeX
    -0.71
    adia
    -0.71
    perse
    -0.69
    inson
    -0.67
    enders
    -0.65
    ê
    -0.64
    ****
    -0.62
    perial
    -0.61
    LAN
    -0.61
    POSITIVE LOGITS
    ties
    1.30
     kinds
    0.98
    oshenko
    0.88
    iated
    0.86
    iating
    0.82
     amount
    0.81
    etheless
    0.79
     certain
    0.75
     combinations
    0.74
     wavelengths
    0.74
    Act Density 0.015%

    No Known Activations