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

    Neuronpedia

    INDEX
    Explanations

    phrases related to controversial or newsworthy events and topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to controversies and serious incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ++++++++++++++++
    -0.66
    ++++++++
    -0.60
    âĿ
    -0.59
     :=
    -0.57
    -)
    -0.55
     Fold
    -0.55
     Compact
    -0.55
     compact
    -0.54
    ')
    -0.54
    entary
    -0.54
    POSITIVE LOGITS
     culminated
    0.75
     culminating
    0.69
    SPONSORED
    0.69
     triggering
    0.67
     prompted
    0.66
     purportedly
    0.65
     purported
    0.63
     resulted
    0.63
     ostensibly
    0.63
    itled
    0.63
    Act Density 0.849%

    No Known Activations