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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concealing or keeping something secret

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "hiding" or concealment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.90
    etheless
    -0.75
    bably
    -0.73
    anwhile
    -0.73
    signed
    -0.72
    xual
    -0.71
    ersive
    -0.69
    alky
    -0.68
    demand
    -0.67
    interrupted
    -0.66
    POSITIVE LOGITS
    ously
    1.02
     hide
    1.00
     hides
    0.89
     Hide
    0.82
     hid
    0.76
     secrets
    0.75
    iary
    0.74
    buster
    0.74
    VILLE
    0.73
    rets
    0.73
    Act Density 0.008%

    No Known Activations