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

    Neuronpedia

    INDEX
    Explanations

    references to physical structures like dams

    oai_token-act-pair · gpt-3.5-turbo

    references to dams and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.65
     profiling
    -0.63
     XVI
    -0.61
    ģĸ
    -0.61
     Typhoon
    -0.61
    ACP
    -0.60
    avorite
    -0.60
     Garner
    -0.59
     Citation
    -0.59
    cki
    -0.59
    POSITIVE LOGITS
    ascus
    1.43
    ned
    1.20
    ukong
    1.20
    mit
    1.13
    sels
    1.10
    nation
    1.07
    sel
    1.04
    aged
    1.02
    ming
    0.99
    pered
    0.98
    Act Density 0.040%

    No Known Activations