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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases beginning with 'to.'

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing types or categories of situations and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pigs
    -0.78
     Seconds
    -0.74
    APS
    -0.73
     Sands
    -0.71
     Signs
    -0.70
     Volunteers
    -0.70
    gow
    -0.70
    idelines
    -0.69
     Burnett
    -0.69
     Doors
    -0.68
    POSITIVE LOGITS
     thing
    1.00
     scenario
    0.83
     behavior
    0.82
     activity
    0.80
     cooperation
    0.79
     vitri
    0.78
     polarization
    0.78
     situation
    0.78
     shenan
    0.76
     endeavor
    0.76
    Act Density 0.036%

    No Known Activations