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

    Neuronpedia

    INDEX
    Explanations

    phrases that express a basis or foundation for claims or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagHelper
    -0.63
     QtGui
    -0.54
     Genn
    -0.53
     Ginn
    -0.52
     Allgeme
    -0.51
     aikana
    -0.48
     Smyth
    -0.47
     Pflicht
    -0.47
     demain
    -0.47
    Serialize
    -0.47
    POSITIVE LOGITS
     Based
    1.29
    Based
    1.27
     based
    1.26
    BASED
    1.26
     BASED
    1.21
    based
    1.17
     basé
    1.13
     basée
    1.06
     beruht
    1.00
     basing
    0.98
    Act Density 0.179%

    No Known Activations