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

    Neuronpedia

    INDEX
    Explanations

    adverbs that indicate how an action is carried out

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating manner or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rite
    -0.68
    tein
    -0.67
     AJ
    -0.66
    oute
    -0.63
    rys
    -0.63
     ACL
    -0.60
    hao
    -0.59
     TY
    -0.57
     LH
    -0.57
     privilege
    -0.57
    POSITIVE LOGITS
     afterward
    0.77
     thereafter
    0.77
     during
    0.75
     throughout
    0.74
     afterwards
    0.74
     ILCS
    0.74
     clothed
    0.72
     outdoors
    0.71
     onstage
    0.70
     indoors
    0.69
    Act Density 0.149%

    No Known Activations