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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hiding or concealing information or actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Ħ¢
    -1.07
    orough
    -1.06
    ctive
    -1.02
    ombat
    -1.00
    odcast
    -0.97
    signed
    -0.95
    ammy
    -0.94
    oker
    -0.92
    sych
    -0.91
    iod
    -0.91
    POSITIVE LOGITS
    ously
    1.46
    away
    1.38
     behind
    1.10
     hide
    1.02
    doors
    1.01
     hid
    0.98
     away
    0.93
     secrets
    0.92
    aways
    0.92
     hiding
    0.91
    Act Density 0.864%

    No Known Activations