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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the addition of information or the expressing of an opinion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     thermomix
    -0.93
     Confe
    -0.79
     Simult
    -0.78
     vito
    -0.75
     pican
    -0.74
     canel
    -0.73
     churrasco
    -0.73
     socie
    -0.72
     ecclesias
    -0.71
     Consig
    -0.69
    POSITIVE LOGITS
     added
    0.95
     adding
    0.93
    added
    0.89
     add
    0.89
     ADDED
    0.85
     adds
    0.84
     Added
    0.82
    adding
    0.81
     addition
    0.79
    Added
    0.78
    Act Density 0.058%

    No Known Activations