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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases or signal the beginning of a text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.59
    addGap
    -0.57
    icata
    -0.57
     незавершена
    -0.55
     interest
    -0.54
     interests
    -0.51
    udes
    -0.51
     cultures
    -0.51
     autorytatywna
    -0.50
     kasarigan
    -0.50
    POSITIVE LOGITS
     screaming
    0.78
     screamed
    0.77
     sobbed
    0.77
     sobbing
    0.76
     screams
    0.73
     yelling
    0.71
     anguish
    0.70
     frantically
    0.70
     pleading
    0.69
     scream
    0.68
    Act Density 0.166%

    No Known Activations