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

    Neuronpedia

    INDEX
    Explanations

    references to vague or nonspecific items and concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    reactstrap
    -0.55
     industriales
    -0.50
     lisää
    -0.49
     tekem
    -0.49
     termica
    -0.48
    います
    -0.48
     méta
    -0.47
    みましょう
    -0.46
     antaranya
    -0.46
    contri
    -0.46
    POSITIVE LOGITS
     []:
    0.72
    
    0.71
    avigation
    0.69
    dafx
    0.68
    %)$
    0.66
     surla
    0.66
    ########.
    0.65
    WriteTagHelper
    0.64
    folger
    0.63
    новниш
    0.63
    Act Density 0.020%

    No Known Activations