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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative effects and comparisons in scientific findings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    arResult
    -0.61
    ainville
    -0.59
     saites
    -0.58
     TextInputType
    -0.56
    WriteTagHelper
    -0.54
    DOCTYPE
    -0.54
     inmediata
    -0.52
    }$_
    -0.52
    afficheront
    -0.51
    nthesis
    -0.51
    POSITIVE LOGITS
    ViewInit
    0.63
     OMITBAD
    0.56
    parsedMessage
    0.55
    <?,
    0.50
    ниципа
    0.50
    InstanceState
    0.49
     Chwiliwch
    0.47
    InteropServices
    0.46
     intptr
    0.45
    ್ದ
    0.45
    Act Density 0.063%

    No Known Activations