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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the act of being first to do something or taking initiative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tic
    -0.21
    ÄĻd
    -0.16
    -dr
    -0.16
    ôt
    -0.15
     retention
    -0.15
     carriers
    -0.14
    ên
    -0.14
    arin
    -0.14
     Bolton
    -0.14
    umbo
    -0.14
    POSITIVE LOGITS
    oley
    0.16
    TRS
    0.14
     sayf
    0.14
    dfa
    0.14
    elle
    0.14
    oom
    0.14
    afari
    0.14
    pret
    0.13
    apat
    0.13
    icer
    0.13
    Act Density 0.011%

    No Known Activations