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

    Neuronpedia

    INDEX
    Explanations

    key concepts and definitions within structured or formal texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irit
    -0.16
    asso
    -0.15
    úde
    -0.14
    urg
    -0.14
    uset
    -0.14
    gary
    -0.14
    asha
    -0.14
    纪
    -0.14
    udit
    -0.13
    udic
    -0.13
    POSITIVE LOGITS
     term
    0.15
     Holly
    0.15
     RT
    0.14
    /Instruction
    0.14
     hod
    0.14
    umi
    0.13
     Gent
    0.13
     XM
    0.13
    .trailing
    0.13
     purpose
    0.13
    Act Density 0.061%

    No Known Activations