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

    Neuronpedia

    INDEX
    Explanations

    phrases related to secrecy or hiding

    oai_token-act-pair · gpt-3.5-turbo

    references to secrecy and hidden information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reau
    -0.84
     spons
    -0.75
    erto
    -0.74
    utra
    -0.67
    udeb
    -0.66
    akeru
    -0.65
    ullivan
    -0.64
    isher
    -0.63
    apest
    -0.63
     Pwr
    -0.63
    POSITIVE LOGITS
     lurking
    0.87
     whispers
    0.84
     cloaked
    0.81
     secrets
    0.80
     hidden
    0.79
     anonymity
    0.79
     secret
    0.76
    ogens
    0.76
     whisper
    0.75
     haunt
    0.75
    Act Density 0.676%

    No Known Activations