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

    Neuronpedia

    INDEX
    Explanations

    connections between people and their roles or identities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rest
    -0.15
    imax
    -0.14
    any
    -0.14
    ersh
    -0.14
    itters
    -0.14
     anything
    -0.14
    ÙĨØ´
    -0.14
     anywhere
    -0.13
    hurst
    -0.13
    leur
    -0.13
    POSITIVE LOGITS
     responsible
    0.27
    nearest
    0.23
     nearest
    0.23
    closest
    0.22
     closest
    0.21
     that
    0.20
     responsable
    0.20
     Responsible
    0.19
     ÏĢοÏħ
    0.19
     whose
    0.19
    Act Density 0.451%

    No Known Activations