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

    Neuronpedia

    INDEX
    Explanations

    description of physical objects, structures, and locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of descriptive phrases or clauses within complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Politics
    -0.73
    idays
    -0.71
     Investment
    -0.69
    vernight
    -0.69
     Income
    -0.69
    ategor
    -0.68
     Conquest
    -0.67
     Equity
    -0.67
    Education
    -0.66
     Online
    -0.65
    POSITIVE LOGITS
     resembling
    1.23
     indicating
    1.19
     protr
    1.16
     which
    1.08
     whereas
    1.05
     allowing
    1.04
     thereby
    1.02
     implying
    1.01
     reminiscent
    1.00
     emitting
    0.99
    Act Density 0.239%

    No Known Activations