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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "aren."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Garen" and related references within the context of games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achusetts
    -0.69
     Accuracy
    -0.66
     srfAttach
    -0.64
    urers
    -0.63
    urer
    -0.63
    err
    -0.60
    ered
    -0.59
     methodological
    -0.58
     jerk
    -0.58
     miscarriage
    -0.57
    POSITIVE LOGITS
    emies
    0.85
    ites
    0.82
    heit
    0.82
    ski
    0.80
    stant
    0.80
    ko
    0.78
    thro
    0.77
    thood
    0.76
    thal
    0.75
    't
    0.74
    Act Density 0.015%

    No Known Activations