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

    Neuronpedia

    INDEX
    Explanations

    instances where something is done individually or in a step-by-step manner

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynt
    -0.74
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.62
    ancies
    -0.61
    BG
    -0.59
     directions
    -0.58
    ').
    -0.57
    Fin
    -0.56
    BALL
    -0.55
    QL
    -0.55
    RG
    -0.55
    POSITIVE LOGITS
    undred
    0.81
    atown
    0.79
    ©¶æ
    0.77
    ousand
    0.76
    elfth
    0.72
     twentieth
    0.70
    yip
    0.69
    ixty
    0.67
    enth
    0.67
    many
    0.67
    Act Density 0.082%

    No Known Activations