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

    Neuronpedia

    INDEX
    Explanations

    the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kara
    -0.15
    .rd
    -0.15
    enia
    -0.15
    zelf
    -0.14
    kop
    -0.14
     Bs
    -0.14
    огÑĢа
    -0.14
    optera
    -0.14
    mary
    -0.14
    aven
    -0.14
    POSITIVE LOGITS
    bidden
    0.21
    aging
    0.18
    rtl
    0.17
    mentor
    0.17
    aged
    0.17
    ump
    0.16
    geries
    0.16
    bear
    0.16
    yth
    0.16
    ney
    0.15
    Act Density 0.095%

    No Known Activations