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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achievements or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain punctuation or important statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stuff
    -0.71
     pse
    -0.69
     contrace
    -0.64
     squirrel
    -0.63
     placebo
    -0.62
     fairy
    -0.62
     carrots
    -0.60
     picnic
    -0.59
     crap
    -0.59
     bail
    -0.59
    POSITIVE LOGITS
     Additionally
    1.22
     Whilst
    1.20
    Additionally
    1.18
     Furthermore
    1.15
    Furthermore
    1.12
    Upon
    1.12
    Following
    1.10
     Lastly
    1.08
    Due
    1.04
     Upon
    1.04
    Act Density 1.007%

    No Known Activations