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

    Neuronpedia

    INDEX
    Explanations

    themes of emotional intensity and complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //{{
    -0.16
    oret
    -0.16
    _ctxt
    -0.15
    cki
    -0.15
    YSTEM
    -0.15
     own
    -0.15
    usto
    -0.15
    (Bit
    -0.14
    ichel
    -0.14
    utsch
    -0.14
    POSITIVE LOGITS
    γον
    0.18
    ness
    0.17
     confines
    0.15
     difference
    0.15
     possibility
    0.14
     sounds
    0.14
    uche
    0.14
     details
    0.14
     Loot
    0.14
     reaches
    0.14
    Act Density 0.294%

    No Known Activations