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

    Neuronpedia

    INDEX
    Explanations

    components and features related to assembly and functionality in a mechanical or structural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Liberation
    -0.15
     dismantle
    -0.14
    utan
    -0.14
     dismant
    -0.14
    Mutable
    -0.13
    etch
    -0.13
    patches
    -0.13
    ArrayOf
    -0.13
    icc
    -0.13
    yg
    -0.13
    POSITIVE LOGITS
     redirects
    0.23
     trap
    0.22
     traps
    0.21
     redirect
    0.20
    redirect
    0.20
    Trap
    0.20
     prevent
    0.19
     trapping
    0.19
    Redirect
    0.19
     Redirect
    0.19
    Act Density 0.171%

    No Known Activations