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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation and consequences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĬ
    -0.17
    ses
    -0.17
    lez
    -0.15
     vet
    -0.15
     ax
    -0.14
     Levine
    -0.14
    eward
    -0.14
    ibus
    -0.14
    .share
    -0.14
    leck
    -0.14
    POSITIVE LOGITS
     happening
    0.16
    ÙĪØ°
    0.15
     happen
    0.14
    ARAM
    0.14
    GroupBox
    0.14
     happens
    0.14
    marvin
    0.14
    itom
    0.14
    ία
    0.14
    .Linked
    0.14
    Act Density 0.158%

    No Known Activations