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

    Neuronpedia

    INDEX
    Explanations

    the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iro
    -0.16
    hores
    -0.15
    leys
    -0.15
    koli
    -0.14
    zers
    -0.14
    paces
    -0.13
    mans
    -0.13
    ipelines
    -0.13
    yms
    -0.13
    iske
    -0.13
    POSITIVE LOGITS
    /or
    0.17
    ifice
    0.16
    acles
    0.16
    èī²çļĦ
    0.14
    phans
    0.14
    iosk
    0.13
     allied
    0.13
     transit
    0.13
    Messaging
    0.13
    iÅŁim
    0.13
    Act Density 0.235%

    No Known Activations