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

    Neuronpedia

    INDEX
    Explanations

    contrasting phrases and expressions of moderation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alto
    -0.17
    éf
    -0.15
    è¼Ŀ
    -0.15
    779
    -0.14
    lip
    -0.14
    ahun
    -0.14
    aru
    -0.14
    abinet
    -0.14
     apart
    -0.14
    ondon
    -0.14
    POSITIVE LOGITS
     increase
    0.24
     enough
    0.24
     Increase
    0.23
     increased
    0.22
    å¢Ĺ
    0.22
    increase
    0.20
     sufficient
    0.20
     Enough
    0.19
    _increase
    0.19
     ÑĥвелиÑĩ
    0.19
    Act Density 0.007%

    No Known Activations