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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preparation or anticipation of future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nd
    -0.17
    leans
    -0.16
    c
    -0.16
    hood
    -0.16
    allback
    -0.15
    rish
    -0.15
    dance
    -0.14
    -paper
    -0.14
    seau
    -0.14
    faction
    -0.14
    POSITIVE LOGITS
    ä¼į
    0.17
    884
    0.16
    868
    0.16
    OnError
    0.15
    äng
    0.15
    urette
    0.15
    721
    0.14
    egen
    0.14
    740
    0.14
     нÑĮого
    0.14
    Act Density 0.018%

    No Known Activations