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

    Neuronpedia

    INDEX
    Explanations

    references to influence and its various impacts in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iska
    -0.17
    nem
    -0.16
    isser
    -0.16
    location
    -0.16
    place
    -0.15
    ish
    -0.15
    atis
    -0.15
    mie
    -0.15
    chester
    -0.14
    malink
    -0.14
    POSITIVE LOGITS
    åĬĽçļĦ
    0.18
    uated
    0.18
    uating
    0.17
    627
    0.16
    åĬĽ
    0.16
     factors
    0.16
    ively
    0.16
    hpp
    0.15
    ential
    0.15
     upon
    0.15
    Act Density 0.022%

    No Known Activations