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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing personal opinions and thoughts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating honesty or directness in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     backdrop
    -0.75
     retreating
    -0.73
     ransom
    -0.72
     unden
    -0.69
     dissolve
    -0.63
     enshr
    -0.63
    coming
    -0.58
    §
    -0.57
     strand
    -0.56
     arise
    -0.56
    POSITIVE LOGITS
     NEVER
    0.88
     ROCK
    0.75
     amazed
    0.70
     ain
    0.70
     THANK
    0.69
     LOVE
    0.68
    ZI
    0.65
     impressed
    0.64
     neither
    0.64
     nobody
    0.64
    Act Density 0.236%

    No Known Activations