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

    Neuronpedia

    INDEX
    Explanations

    references to communication or information sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gezond
    -0.60
     virke
    -0.58
    amba
    -0.58
     Calhoun
    -0.57
     Humphries
    -0.57
     Schmitt
    -0.56
    gående
    -0.56
     unfavorable
    -0.55
     Stanley
    -0.55
    bundet
    -0.55
    POSITIVE LOGITS
    Told
    1.50
     tells
    1.49
     Tells
    1.47
     Tell
    1.47
     Told
    1.45
     tell
    1.44
    Tell
    1.44
     TELL
    1.42
     told
    1.41
    told
    1.40
    Act Density 0.068%

    No Known Activations