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

    Neuronpedia

    INDEX
    Explanations

    expressions of kindness and sympathetic attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.78
     Monfieur
    -0.77
    ſelf
    -0.76
     Efq
    -0.75
     leaſt
    -0.75
     myſelf
    -0.75
     ſche
    -0.74
     strtotime
    -0.73
    ificantly
    -0.71
    Referencer
    -0.71
    POSITIVE LOGITS
     kind
    4.46
    kind
    4.07
     Kind
    3.97
    Kind
    3.88
     KIND
    3.60
    KIND
    3.17
     sort
    2.84
     kinds
    2.59
     kinda
    2.50
    kinds
    2.40
    Act Density 0.064%

    No Known Activations