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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing expectations or beliefs about outcomes and experiences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WarningLevel
    -0.47
     doPost
    -0.47
    dword
    -0.46
     choi
    -0.45
     HttpServlet
    -0.44
    WEBPACK
    -0.44
     draughts
    -0.44
    Checkbox
    -0.43
    roughs
    -0.43
     Exactos
    -0.43
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.68
    DockStyle
    0.67
     AssemblyCulture
    0.61
     devaient
    0.57
     mergeFrom
    0.56
     presentará
    0.56
    enumi
    0.56
     expecting
    0.54
    AnimationsModule
    0.54
     antemano
    0.53
    Act Density 0.210%

    No Known Activations