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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time frames or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginning
    -0.22
    sis
    -0.19
     begin
    -0.19
     beginnings
    -0.18
     Beginning
    -0.18
     begins
    -0.18
    Beginning
    -0.17
    begin
    -0.17
     end
    -0.17
     Begin
    -0.17
    POSITIVE LOGITS
     next
    0.21
     month
    0.19
    next
    0.17
    -month
    0.17
     Month
    0.15
    wner
    0.15
    month
    0.15
    currentColor
    0.14
    edy
    0.14
    æľĪ
    0.14
    Act Density 0.022%

    No Known Activations