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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.46
     Through
    -0.41
    providedIn
    -0.40
     intéressante
    -0.40
     interessante
    -0.39
     Thus
    -0.37
     Importantly
    -0.36
     interesting
    -0.36
     through
    -0.36
    Through
    -0.35
    POSITIVE LOGITS
    Sure
    1.16
     Sure
    1.10
     sure
    1.02
    Seriously
    0.98
    sure
    0.98
     Seriously
    0.96
     seriously
    0.87
     Yeah
    0.84
    seriously
    0.84
     Heck
    0.82
    Act Density 0.305%

    No Known Activations