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

    Neuronpedia

    INDEX
    Explanations

    dates and months of events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amais
    -1.74
    STEM
    -1.71
    quo
    -1.62
    untu
    -1.60
    xico
    -1.60
    obbsee
    -1.58
    fessor
    -1.58
    oved
    -1.55
    ellow
    -1.53
    unge
    -1.53
    POSITIVE LOGITS
     et
    1.59
     tragedy
    1.55
     motive
    1.52
    wood
    1.51
    works
    1.48
     blows
    1.42
    ikh
    1.42
     interference
    1.39
     implications
    1.39
    ledge
    1.38
    Act Density 0.098%

    No Known Activations