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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the comparative or superlative form along with contextual references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.80
    #
    -0.78
     MonoBehaviour
    -0.76
    ynchronously
    -0.74
     Wicidata
    -0.67
    etcode
    -0.66
    PreferredItem
    -0.66
    CWE
    -0.65
    ++]=
    -0.63
    ngthen
    -0.63
    POSITIVE LOGITS
     than
    1.35
    than
    0.86
     THAN
    0.85
     niż
    0.82
    THAN
    0.82
    Than
    0.77
     hơn
    0.73
     Than
    0.69
     než
    0.68
     truer
    0.67
    Act Density 0.255%

    No Known Activations