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

    Neuronpedia

    INDEX
    Explanations

    instances of conversational transitions and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ø®ÙĪ
    -0.17
    .once
    -0.16
    оло
    -0.15
    angs
    -0.15
    ahren
    -0.15
    .initialize
    -0.15
    लत
    -0.14
     Phú
    -0.14
     Hughes
    -0.14
    ownik
    -0.14
    POSITIVE LOGITS
    eworld
    0.15
    ola
    0.15
     Quantity
    0.15
    VT
    0.14
    ez
    0.14
    ัศ
    0.14
    chine
    0.14
    ene
    0.14
    è£ľ
    0.13
    iden
    0.13
    Act Density 0.040%

    No Known Activations