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

    Neuronpedia

    INDEX
    Explanations

    contexts involving uncertainty and varying degrees of support or evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urse
    -0.16
    omination
    -0.15
     Duffy
    -0.15
     labs
    -0.14
    INVAL
    -0.14
     logs
    -0.14
     twin
    -0.13
    ispers
    -0.13
     Labs
    -0.13
    erral
    -0.13
    POSITIVE LOGITS
     stuff
    0.26
     evidence
    0.21
     footage
    0.20
     legislation
    0.20
     Machinery
    0.20
     Legislation
    0.19
    stuff
    0.19
     groundwork
    0.19
     information
    0.18
     Stuff
    0.18
    Act Density 0.286%

    No Known Activations