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

    Neuronpedia

    INDEX
    Explanations

    significant actions or decisions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yl
    -0.14
     Tell
    -0.14
     Tells
    -0.14
    quette
    -0.14
    eder
    -0.13
    tle
    -0.13
     Changed
    -0.13
    emaakt
    -0.13
     Dit
    -0.13
    pf
    -0.13
    POSITIVE LOGITS
     follows
    0.44
     comes
    0.38
     follow
    0.35
     Follow
    0.34
    Follow
    0.32
    follow
    0.31
    comes
    0.30
    .follow
    0.30
     Comes
    0.29
     FOLLOW
    0.27
    Act Density 0.106%

    No Known Activations