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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms or keywords

    oai_token-act-pair · gpt-3.5-turbo

    specific references to technology and digital platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.81
    ocate
    -0.73
    hower
    -0.72
    oulos
    -0.72
    ngth
    -0.71
    orically
    -0.71
    jriwal
    -0.70
    phabet
    -0.69
    eful
    -0.67
    avorite
    -0.67
    POSITIVE LOGITS
     occasions
    1.24
     basis
    0.95
     shores
    0.91
     eve
    0.88
     occasion
    0.83
     Island
    0.82
     whim
    0.82
    ilts
    0.81
     forums
    0.77
     behalf
    0.77
    Act Density 0.288%

    No Known Activations