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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or control

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "the" and other possessive pronouns indicating ownership or relationship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NESS
    -0.80
    MAP
    -0.72
    HAEL
    -0.70
     coward
    -0.64
     Guilty
    -0.64
    ĨĴ
    -0.63
    DIV
    -0.61
    åº
    -0.61
     Mats
    -0.61
    GMT
    -0.60
    POSITIVE LOGITS
     knack
    0.94
    been
    0.92
    stood
    0.83
     chance
    0.83
     opportunity
    0.81
    ailable
    0.75
     privileges
    0.75
     towed
    0.74
    ointed
    0.70
    icum
    0.70
    Act Density 0.289%

    No Known Activations