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

    Neuronpedia

    INDEX
    Explanations

    words related to concealment or secrecy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hide" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombat
    -0.80
    ctive
    -0.78
    ammy
    -0.76
    onian
    -0.69
    ersive
    -0.69
    oker
    -0.69
    orough
    -0.68
    union
    -0.67
    signed
    -0.67
    FK
    -0.66
    POSITIVE LOGITS
    ously
    1.03
    away
    0.82
     hid
    0.80
     hide
    0.79
     hides
    0.75
     behind
    0.75
     hiding
    0.75
     Clo
    0.75
    rets
    0.73
     secrets
    0.71
    Act Density 0.026%

    No Known Activations