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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating superiority or inferiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĢij
    -0.16
    esktop
    -0.16
    adlo
    -0.16
    DonaldTrump
    -0.16
    InstanceState
    -0.15
    umo
    -0.15
    usercontent
    -0.14
    fty
    -0.14
    achuset
    -0.14
    ätt
    -0.14
    POSITIVE LOGITS
     ever
    0.24
     usual
    0.22
     what
    0.19
     expected
    0.19
     meets
    0.19
     than
    0.19
     they
    0.18
     necessary
    0.18
     originally
    0.18
     anticipated
    0.18
    Act Density 0.071%

    No Known Activations