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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sometime" indicating future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsen
    -0.81
    elson
    -0.77
    Reviewer
    -0.76
    iants
    -0.76
    oos
    -0.75
    andi
    -0.74
    egal
    -0.72
    imilation
    -0.72
    elfare
    -0.71
    ading
    -0.69
    POSITIVE LOGITS
     else
    0.98
    Else
    0.88
     Ago
    0.87
    morning
    0.86
     ago
    0.86
     thereafter
    0.84
     ILCS
    0.83
    theless
    0.81
     unspecified
    0.80
     mornings
    0.77
    Act Density 0.006%

    No Known Activations