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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "difference" and descriptions of comparisons

    oai_token-act-pair · gpt-3.5-turbo

    References to differences or distinctions between various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rollers
    -0.83
    vez
    -0.82
     DRAGON
    -0.75
    ATA
    -0.75
    mberg
    -0.72
    ODE
    -0.72
    atom
    -0.69
    idden
    -0.66
    stra
    -0.66
    odes
    -0.65
    POSITIVE LOGITS
    yip
    0.90
     between
    0.87
    erence
    0.85
    between
    0.85
     maker
    0.81
    iveness
    0.81
    iculty
    0.78
     Between
    0.75
    aroo
    0.75
    ials
    0.74
    Act Density 0.022%

    No Known Activations