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

    Neuronpedia

    INDEX
    Explanations

    colloquial expressions and phrases related to subtle distinctions or critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.65
     ſtre
    -0.62
    EndContext
    -0.62
     anſ
    -0.60
    ClientSize
    -0.59
    ActivityResult
    -0.59
     ſta
    -0.58
     hemispheres
    -0.58
     fhort
    -0.58
     reaſon
    -0.58
    POSITIVE LOGITS
     anti
    0.90
     liberal
    0.69
    ANTI
    0.68
     Anti
    0.68
     non
    0.68
     ANTI
    0.64
    :✨
    0.64
     partisan
    0.62
     pro
    0.62
    anti
    0.61
    Act Density 0.525%

    No Known Activations