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

    Neuronpedia

    INDEX
    Explanations

    communications involving people sharing personal information or making requests

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to criminal activities and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Critics
    -0.81
     proponents
    -0.75
     argues
    -0.74
     advocates
    -0.71
     rhet
    -0.71
    uably
    -0.67
     asserts
    -0.66
     arguably
    -0.65
     incentiv
    -0.65
     initiatives
    -0.64
    POSITIVE LOGITS
     tresp
    0.79
    yip
    0.76
     mosqu
    0.71
     downstairs
    0.71
     trespass
    0.70
    —"
    0.69
     evacuate
    0.69
     daddy
    0.68
     SOLD
    0.67
    LOAD
    0.67
    Act Density 0.658%

    No Known Activations