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

    Neuronpedia

    INDEX
    Explanations

    stressed and negative emotions or actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to distress, discomfort, and noncompliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     examiner
    -0.60
    DragonMagazine
    -0.55
     Norn
    -0.54
     Summit
    -0.53
     explorer
    -0.52
     deed
    -0.51
     Annotations
    -0.51
    senal
    -0.50
     Transition
    -0.50
     Rover
    -0.49
    POSITIVE LOGITS
    alled
    0.84
    ited
    0.78
    amb
    0.76
    bled
    0.76
    ped
    0.76
    icked
    0.76
    ended
    0.75
    ated
    0.74
    ined
    0.74
    ivably
    0.74
    Act Density 0.551%

    No Known Activations