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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    075
    -0.16
    462
    -0.16
    ouve
    -0.15
    ucas
    -0.15
    StateChanged
    -0.14
    ombine
    -0.14
    formed
    -0.14
    ampler
    -0.14
    aring
    -0.14
    unes
    -0.13
    POSITIVE LOGITS
     goes
    0.24
     must
    0.19
     extends
    0.17
     extended
    0.16
     Goes
    0.16
     extend
    0.15
    egasus
    0.15
     special
    0.15
     Special
    0.15
     go
    0.15
    Act Density 0.021%

    No Known Activations