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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to motivation and pushing boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /by
    -0.17
    kt
    -0.17
    jac
    -0.16
    fred
    -0.16
    uco
    -0.16
    bsolute
    -0.15
    vez
    -0.15
    kir
    -0.15
    throp
    -0.15
    ullen
    -0.14
    POSITIVE LOGITS
     aside
    0.35
     buttons
    0.30
     boundaries
    0.28
     envelope
    0.28
     harder
    0.27
     forward
    0.27
     limits
    0.27
     ahead
    0.26
    buttons
    0.25
     hard
    0.25
    Act Density 0.041%

    No Known Activations