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

    Neuronpedia

    INDEX
    Explanations

    phrases related to control and power

    oai_token-act-pair · gpt-3.5-turbo

    phrases regarding loss of control or governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rouse
    -0.71
    ME
    -0.71
    tu
    -0.69
    dayName
    -0.68
    ullah
    -0.65
    ucc
    -0.65
    onna
    -0.65
    NL
    -0.65
    KK
    -0.64
     teasp
    -0.64
    POSITIVE LOGITS
    thood
    0.70
     the
    0.66
     Hearts
    0.65
    ership
    0.63
     reins
    0.63
     course
    0.62
     ownership
    0.60
     affairs
    0.60
     Realms
    0.59
    eer
    0.59
    Act Density 0.116%

    No Known Activations