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

    Neuronpedia

    INDEX
    Explanations

    phrases related to verification processes

    oai_token-act-pair · gpt-3.5-turbo

    words related to verification and confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.87
     Sparrow
    -0.82
    benefit
    -0.70
    kers
    -0.67
    hoff
    -0.66
    lot
    -0.66
    Kin
    -0.65
    ngth
    -0.64
    quartered
    -0.64
    sbm
    -0.64
    POSITIVE LOGITS
     verify
    0.85
    ifying
    0.76
     verification
    0.75
    irmation
    0.72
    ificate
    0.68
     verified
    0.67
     Kavanaugh
    0.66
     verifying
    0.65
     validity
    0.65
    ifies
    0.65
    Act Density 0.009%

    No Known Activations