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

    Neuronpedia

    INDEX
    Explanations

    relational words that imply connections and interactions between characters or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.16
    lerdi
    -0.14
    ãĥ¬ãĥ³
    -0.14
    iquer
    -0.13
    rega
    -0.13
    ongan
    -0.13
    icast
    -0.13
    .about
    -0.13
    awah
    -0.13
    isbury
    -0.13
    POSITIVE LOGITS
     hour
    0.17
     stars
    0.16
     Lord
    0.16
     Father
    0.16
     very
    0.15
     sound
    0.15
    (ir
    0.14
     Hour
    0.14
    oph
    0.14
     same
    0.14
    Act Density 0.136%

    No Known Activations