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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "next to" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" in various contexts, indicating a focus on directional language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.77
    é¾
    -0.72
    OY
    -0.69
    Includes
    -0.68
    esi
    -0.68
    inet
    -0.68
    wcs
    -0.67
    UFF
    -0.67
    OB
    -0.66
    anke
    -0.66
    POSITIVE LOGITS
     him
    0.84
     hers
    0.75
    rium
    0.74
     them
    0.67
     the
    0.66
     theirs
    0.64
    sighted
    0.64
     ours
    0.63
     Interstate
    0.62
     each
    0.62
    Act Density 0.037%

    No Known Activations