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

    Neuronpedia

    INDEX
    Explanations

    technical details and specifications related to products and their materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Liberation
    -0.15
    ainers
    -0.14
     Lit
    -0.14
    strained
    -0.14
    enant
    -0.14
    Lit
    -0.14
    elin
    -0.14
    shortcut
    -0.14
    Forge
    -0.13
    antz
    -0.13
    POSITIVE LOGITS
     trap
    0.26
     rep
    0.26
     traps
    0.25
     resist
    0.24
     redirects
    0.23
    Trap
    0.23
     Redirect
    0.22
    trap
    0.21
     prevent
    0.21
     Trap
    0.21
    Act Density 0.149%

    No Known Activations