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

    Neuronpedia

    INDEX
    Explanations

    terms related to publishing and publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jara
    -0.79
     HttpHeaders
    -0.78
    Zx
    -0.69
     Cantor
    -0.69
    makeConstraints
    -0.68
     Aida
    -0.67
     '\\;'
    -0.67
     Seton
    -0.67
     Mep
    -0.67
    vspace
    -0.67
    POSITIVE LOGITS
     traits
    0.96
     trait
    0.92
    anim
    0.90
     Trait
    0.88
     Traits
    0.84
    Anim
    0.84
    traits
    0.80
     anim
    0.78
     whom
    0.76
    Trait
    0.75
    Act Density 0.089%

    No Known Activations