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

    Neuronpedia

    INDEX
    Explanations

    phrases related to modeling and measurement in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     am
    -0.47
    Brains
    -0.44
     use
    -0.43
     tanke
    -0.43
     Trust
    -0.42
     jal
    -0.42
    ab
    -0.42
     believe
    -0.41
    Trust
    -0.41
    ib
    -0.41
    POSITIVE LOGITS
     linkovi
    0.99
    ThroughAttribute
    0.91
     conveys
    0.85
     conveyed
    0.81
     conveying
    0.78
     depicting
    0.78
     capturing
    0.77
    findpost
    0.77
     captures
    0.77
     convey
    0.77
    Act Density 0.831%

    No Known Activations