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

    Neuronpedia

    INDEX
    Explanations

    social surveys or studies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     cones
    -0.75
    lets
    -0.69
    nen
    -0.67
    ynthesis
    -0.65
    ynt
    -0.64
    acas
    -0.60
    NZ
    -0.60
     generations
    -0.60
     havens
    -0.59
    metic
    -0.58
    POSITIVE LOGITS
    iple
    0.73
     guiActiveUnfocused
    0.72
     Reserved
    0.70
    rait
    0.66
     Dynamics
    0.65
    ibur
    0.65
    purpose
    0.64
    ;;;;;;;;;;;;
    0.63
    EO
    0.62
    oday
    0.62
    Act Density 0.077%

    No Known Activations