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

    Neuronpedia

    INDEX
    Explanations

    occurrences of conjunctions and relevant phrases indicating comparison or relationship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oka
    -0.17
    udit
    -0.15
    oji
    -0.15
    angel
    -0.15
    odos
    -0.15
    ippi
    -0.14
    ulas
    -0.14
    eve
    -0.14
    cesso
    -0.14
     neust
    -0.14
    POSITIVE LOGITS
     beyond
    0.26
     the
    0.23
     its
    0.22
     Beyond
    0.21
    /as
    0.20
    Beyond
    0.19
     Its
    0.18
    eyond
    0.18
    /of
    0.17
     their
    0.16
    Act Density 0.113%

    No Known Activations