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

    Neuronpedia

    INDEX
    Explanations

    phrases reflecting personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĸдно
    -0.16
    dre
    -0.15
    stroy
    -0.13
    ÑĪов
    -0.13
    ibrary
    -0.13
    ãĥ£
    -0.13
    ells
    -0.12
    iko
    -0.12
     boyc
    -0.12
    поÑĢ
    -0.12
    POSITIVE LOGITS
     talking
    0.69
     referring
    0.55
     talk
    0.54
     Talking
    0.52
     refer
    0.49
    Talking
    0.49
     speaking
    0.48
    -talk
    0.44
     refers
    0.43
     talks
    0.42
    Act Density 0.201%

    No Known Activations