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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate possession or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    been
    -0.65
     strugg
    -0.60
     Palest
    -0.59
     Tsukuyomi
    -0.59
     Unsure
    -0.58
     Ort
    -0.57
    liest
    -0.56
    esi
    -0.56
     partName
    -0.56
    sa
    -0.56
    POSITIVE LOGITS
    minster
    0.79
    undown
    0.77
    asses
    0.72
    irgin
    0.69
    ocaust
    0.67
    vation
    0.65
    ipment
    0.64
     oneself
    0.63
    thood
    0.63
    ogle
    0.62
    Act Density 0.126%

    No Known Activations