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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deep emotions or profound concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deep" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orious
    -0.83
    pload
    -0.74
    ICAN
    -0.71
    roma
    -0.70
    icans
    -0.69
    oppable
    -0.69
    icks
    -0.68
     Speedway
    -0.68
    jee
    -0.67
    uthor
    -0.67
    POSITIVE LOGITS
     vein
    1.06
    ened
    1.03
     seeded
    0.93
     breaths
    0.83
     penetration
    0.81
     pockets
    0.81
     deep
    0.79
     depth
    0.79
     dive
    0.78
     enough
    0.77
    Act Density 0.024%

    No Known Activations