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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and structural similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RSSSF
    -0.82
     myſelf
    -0.81
    StoryboardSegue
    -0.77
     raiſ
    -0.74
    )";
    -0.72
     Efq
    -0.72
     Osiris
    -0.70
     cdti
    -0.70
     Phry
    -0.70
     Anſ
    -0.70
    POSITIVE LOGITS
     the
    0.63
     like
    0.55
     a
    0.55
     those
    0.53
     Like
    0.52
     celui
    0.49
     ahogy
    0.49
     ex
    0.48
     précédents
    0.48
     his
    0.47
    Act Density 0.391%

    No Known Activations