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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical interaction or movement

    oai_token-act-pair · gpt-3.5-turbo

    actions involving physical movements or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redes
    -0.71
    KEN
    -0.71
     specialization
    -0.70
    Develop
    -0.64
    conom
    -0.63
    ovi
    -0.62
     Experts
    -0.61
    nation
    -0.61
    unity
    -0.60
    WASHINGTON
    -0.60
    POSITIVE LOGITS
    rily
    0.95
     him
    0.84
     glances
    0.78
     herself
    0.76
     his
    0.76
     himself
    0.76
    stretched
    0.76
     onto
    0.75
     clenched
    0.74
     her
    0.74
    Act Density 0.249%

    No Known Activations