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

    Neuronpedia

    INDEX
    Explanations

    words related to danger or hazardous situations

    oai_token-act-pair · gpt-3.5-turbo

    references to danger or hazardous situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omics
    -0.75
     Simpl
    -0.69
    iture
    -0.69
     remem
    -0.69
     attends
    -0.67
     sits
    -0.67
    Sing
    -0.66
     announces
    -0.66
    onut
    -0.64
    iversary
    -0.64
    POSITIVE LOGITS
     dangerous
    3.39
    danger
    2.49
     hazardous
    2.21
     deadly
    2.11
     Dangerous
    2.10
     perilous
    2.09
     risky
    1.98
     harmful
    1.95
     unsafe
    1.92
     dangerously
    1.86
    Act Density 0.035%

    No Known Activations