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

    Neuronpedia

    INDEX
    Explanations

    frequency words and conjunctions that indicate relationships or comparisons within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alban
    -0.15
    ayi
    -0.14
    .Dock
    -0.14
    arm
    -0.14
     offsets
    -0.14
    arty
    -0.14
    aits
    -0.14
    asd
    -0.13
    åĢį
    -0.13
    ıi
    -0.13
    POSITIVE LOGITS
    .gdx
    0.15
    chn
    0.15
    egal
    0.15
    ey
    0.15
    égor
    0.15
    æ´ŀ
    0.14
    otas
    0.14
    ornado
    0.14
    iolet
    0.14
    ossa
    0.14
    Act Density 0.001%

    No Known Activations