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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific male subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TNT
    -0.65
     Voltage
    -0.62
     §§
    -0.61
     ___
    -0.59
     SYSTEM
    -0.59
     +/-
    -0.58
     AWS
    -0.58
     reversal
    -0.58
     SERVICE
    -0.58
     Punjab
    -0.57
    POSITIVE LOGITS
    zbollah
    1.55
    resy
    1.44
    idi
    1.44
    ather
    1.43
    avier
    1.42
    aven
    1.41
    gemony
    1.36
    reditary
    1.30
    ldon
    1.30
    aling
    1.26
    Act Density 0.147%

    No Known Activations