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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote an effort to advance or challenge limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    سد
    -0.16
    uada
    -0.16
    throp
    -0.15
    ezier
    -0.15
    jac
    -0.15
    uvo
    -0.15
    uco
    -0.15
    ebek
    -0.14
    eker
    -0.14
    bsolute
    -0.14
    POSITIVE LOGITS
     aside
    0.34
    -button
    0.31
    button
    0.30
     buttons
    0.29
    buttons
    0.28
    back
    0.28
    BUTTON
    0.28
     boundaries
    0.27
     forward
    0.25
     harder
    0.25
    Act Density 0.036%

    No Known Activations