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

    Neuronpedia

    INDEX
    Explanations

    terms related to web development and data queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     here
    -0.35
     however
    -0.35
     about
    -0.33
     though
    -0.33
     оно
    -0.32
     when
    -0.31
     whereas
    -0.30
    ψε
    -0.30
     then
    -0.30
     although
    -0.30
    POSITIVE LOGITS
     с
    0.77
     и
    0.77
     для
    0.75
     или
    0.66
    ,
    0.58
     verschiedener
    0.58
     из
    0.57
     в
    0.57
     на
    0.56
     (
    0.56
    Act Density 0.015%

    No Known Activations