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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating addition or inclusion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ẻ
    -0.15
    405
    -0.15
    Ĵ
    -0.14
    ilan
    -0.14
    æĥij
    -0.14
    ite
    -0.14
    .backends
    -0.13
    aginator
    -0.13
     behalf
    -0.13
    pery
    -0.13
    POSITIVE LOGITS
     being
    0.22
     obvious
    0.20
    being
    0.18
     пÑĢоÑĩ
    0.17
    ordinal
    0.16
     Being
    0.16
     usual
    0.16
     regular
    0.16
    regular
    0.15
    ãĥĥãĥī
    0.15
    Act Density 0.034%

    No Known Activations