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

    Neuronpedia

    INDEX
    Explanations

    references to secrets and secrecy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Corral
    -0.59
     Infórmanos
    -0.58
    AccessorTable
    -0.56
    crollView
    -0.56
    IUrlHelper
    -0.55
    pagnes
    -0.55
    ագրություններ
    -0.53
    SIT
    -0.52
    揄
    -0.51
     Strö
    -0.51
    POSITIVE LOGITS
     secret
    1.47
    secret
    1.22
     secretly
    1.16
     secreto
    1.16
     hidden
    1.10
     secrecy
    1.04
     secrets
    0.99
     secr
    0.98
     secretive
    0.93
     verborgen
    0.90
    Act Density 0.089%

    No Known Activations