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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or phrases related to hidden or secret things

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hidden" referring to concealed or obscured concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nia
    -0.82
    annis
    -0.81
     Pwr
    -0.77
    sburgh
    -0.74
    nan
    -0.73
    ctive
    -0.73
    alon
    -0.73
    umbn
    -0.73
    ucc
    -0.72
    adjusted
    -0.71
    POSITIVE LOGITS
     hidden
    0.91
     Hidden
    0.88
     recess
    0.88
     gem
    0.84
     stash
    0.82
     behind
    0.81
     hatch
    0.80
     treasure
    0.79
     underground
    0.78
     depths
    0.78
    Act Density 0.014%

    No Known Activations