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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.65
    Véxase
    -0.58
     архивлан
    -0.53
     itself
    -0.53
    dafx
    -0.51
     Jefus
    -0.50
    Bibliograf
    -0.50
     unknownFields
    -0.50
     fileSize
    -0.50
    ichia
    -0.50
    POSITIVE LOGITS
     were
    0.94
     themselves
    0.88
    themselves
    0.86
     are
    0.85
    were
    0.71
     WERE
    0.66
     SwitchCompat
    0.66
     weren
    0.66
     Were
    0.64
     ARE
    0.64
    Act Density 0.491%

    No Known Activations