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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "come" and its variations, suggesting a focus on temporal expressions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allas
    -0.16
    abra
    -0.15
    ARP
    -0.13
    izzo
    -0.13
    ulação
    -0.13
    holm
    -0.13
    coma
    -0.12
    çĨ
    -0.12
    ventus
    -0.12
    uby
    -0.12
    POSITIVE LOGITS
     hot
    0.31
     amid
    0.29
     amidst
    0.27
     just
    0.25
     days
    0.24
     less
    0.24
     after
    0.23
     weeks
    0.23
     barely
    0.23
     despite
    0.23
    Act Density 0.029%

    No Known Activations