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

    Neuronpedia

    INDEX
    Explanations

    phrases related to caution or warning against certain actions

    oai_token-act-pair · gpt-3.5-turbo

    references to quantity and recommendations regarding action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exhibited
    -0.49
     SetFontSize
    -0.48
    smanship
    -0.48
     premiered
    -0.47
    encer
    -0.47
    encers
    -0.47
     Photograph
    -0.46
    çīĪ
    -0.45
     Bene
    -0.45
     Symphony
    -0.45
    POSITIVE LOGITS
    livion
    0.60
     wilderness
    0.51
    OSP
    0.48
     vulner
    0.48
     recess
    0.47
     reckoning
    0.47
     defenses
    0.47
     ledge
    0.45
     difficulties
    0.45
    tackle
    0.45
    Act Density 1.699%

    No Known Activations