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

    Neuronpedia

    INDEX
    Explanations

    expressions of deservingness or worthiness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating entitlement or merit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullivan
    -0.68
    cross
    -0.66
    gdala
    -0.65
    INS
    -0.60
     plateau
    -0.60
     Ou
    -0.59
     Bohem
    -0.59
    gap
    -0.58
    edd
    -0.57
    law
    -0.56
    POSITIVE LOGITS
     praise
    0.87
     applause
    0.86
     consideration
    0.81
     attention
    0.81
     credit
    0.81
     recognition
    0.81
     precedence
    0.80
     acknowledgement
    0.80
     better
    0.80
    ILY
    0.76
    Act Density 0.042%

    No Known Activations