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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to equivalence or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to equivalence or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ger
    -0.81
    oard
    -0.78
    der
    -0.76
    ben
    -0.76
    stra
    -0.71
     Bomb
    -0.70
    stal
    -0.69
    zan
    -0.66
    hra
    -0.65
    ARD
    -0.64
    POSITIVE LOGITS
     equivalent
    0.97
    ivalent
    0.94
    isons
    0.93
    lihood
    0.90
     equival
    0.80
    awei
    0.79
     equivalents
    0.78
    bnb
    0.78
     oppos
    0.73
    imately
    0.73
    Act Density 0.010%

    No Known Activations