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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confirmation or verification

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confirmed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.94
    ©¶æ
    -0.82
    @#&
    -0.76
    rug
    -0.75
    amaz
    -0.72
    otin
    -0.72
    adr
    -0.70
    ARC
    -0.67
    NetMessage
    -0.67
    ohyd
    -0.67
    POSITIVE LOGITS
     confirmed
    1.13
     confirms
    1.07
    irmation
    1.05
    irmed
    0.99
     confirm
    0.97
    irms
    0.94
     confirmation
    0.92
    confirmed
    0.92
     confirming
    0.87
    esses
    0.78
    Act Density 0.016%

    No Known Activations