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

    Neuronpedia

    INDEX
    Explanations

    words related to possession or attribution

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    issance
    -0.79
     invariably
    -0.73
    utic
    -0.72
    edient
    -0.72
    qqa
    -0.70
    always
    -0.70
    essa
    -0.70
    usterity
    -0.69
    atu
    -0.66
    ani
    -0.66
    POSITIVE LOGITS
     mentioning
    0.80
     mention
    0.73
    handedly
    0.66
     hasht
    0.64
     mentions
    0.64
     jokes
    0.64
     scratch
    0.63
     remotely
    0.62
     nick
    0.61
     curs
    0.61
    Act Density 0.317%

    No Known Activations