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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    oulos
    -0.80
     tomat
    -0.77
     recorder
    -0.76
    razil
    -0.74
     Skydragon
    -0.73
    atoes
    -0.73
    Loading
    -0.72
    CAST
    -0.71
    channelAvailability
    -0.70
    SIGN
    -0.70
    POSITIVE LOGITS
    forced
    1.13
    visible
    1.08
    hart
    1.08
    horn
    1.06
    clus
    1.05
    berg
    1.03
    inen
    1.01
    clusive
    1.01
    accessible
    1.01
    hardt
    1.00
    Act Density 11.284%

    No Known Activations