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

    Neuronpedia

    INDEX
    Explanations

    mentions of television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĭ¤ê°Ģ
    -0.16
    chl
    -0.16
    ated
    -0.16
    uner
    -0.15
    gia
    -0.15
    toi
    -0.15
    uve
    -0.15
    ustralian
    -0.15
    ê»ĺ
    -0.15
    ãģĬãĤĬ
    -0.15
    POSITIVE LOGITS
    manship
    0.25
    biz
    0.21
    runner
    0.20
    ings
    0.20
    piece
    0.19
    rooms
    0.18
    girls
    0.17
    Spatial
    0.17
    matic
    0.16
    ground
    0.16
    Act Density 0.034%

    No Known Activations