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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gezet
    -0.67
     feroit
    -0.61
     pouvoit
    -0.58
     auroit
    -0.56
     gjø
    -0.56
     avoient
    -0.55
     ſind
    -0.55
     mijne
    -0.54
     zijne
    -0.54
    SPJ
    -0.53
    POSITIVE LOGITS
    ,
    0.68
    ↵↵
    0.66
     the
    0.66
     (
    0.61
     in
    0.56
     
    0.55
    ↵
    0.54
     $\
    0.53
    <bos>
    0.51
     of
    0.50
    Act Density 0.694%

    No Known Activations