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

    Neuronpedia

    INDEX
    Explanations

    references to social media or digital media roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referenced
    -0.16
    edor
    -0.15
     backstory
    -0.15
    malar
    -0.15
    unlikely
    -0.15
     referencing
    -0.14
    Regardless
    -0.14
    ocket
    -0.14
     Moo
    -0.13
     backlash
    -0.13
    POSITIVE LOGITS
     occupation
    0.27
     Occupation
    0.22
    occupation
    0.22
     occupations
    0.22
     occupied
    0.21
     (“
    0.21
     –
    0.21
     occup
    0.20
    Occup
    0.20
     Occup
    0.19
    Act Density 0.003%

    No Known Activations