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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating effectiveness, safety, and reliability in medical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.55
     utafitiHapana
    -0.52
    aclk
    -0.50
    concepto
    -0.50
     groans
    -0.48
    DockStyle
    -0.46
    savevideo
    -0.46
     stings
    -0.44
     pomi
    -0.44
    PhysRevLett
    -0.44
    POSITIVE LOGITS
     ModelRenderer
    0.47
     pleaſure
    0.44
     تضيفلها
    0.42
     faſt
    0.41
    ſelf
    0.39
     kohdetta
    0.39
     שוליים
    0.37
    CodedInputStream
    0.36
     Majefty
    0.36
     poffible
    0.35
    Act Density 0.552%

    No Known Activations