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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to concerning issues or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to important issues or topics that require attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Split
    -0.66
    escape
    -0.65
     Split
    -0.64
    opp
    -0.61
    imm
    -0.60
    ideshow
    -0.60
     sprint
    -0.59
    lights
    -0.58
    ops
    -0.57
    MAX
    -0.57
    POSITIVE LOGITS
     concerning
    3.26
    cerning
    1.70
     regarding
    1.67
     respecting
    1.52
     troubling
    1.45
     pertaining
    1.40
     Regarding
    1.35
     worrisome
    1.32
     worrying
    1.29
     relating
    1.28
    Act Density 0.018%

    No Known Activations