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

    Neuronpedia

    INDEX
    Explanations

    terms related to progress and advancement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.42
     Szk
    -0.41
    getLabel
    -0.38
     psiqui
    -0.38
     cage
    -0.36
     coisa
    -0.35
     étn
    -0.34
    <bos>
    -0.32
     juzg
    -0.31
     etiquetas
    -0.31
    POSITIVE LOGITS
     advance
    1.11
    advance
    1.08
     Advance
    1.08
     advancement
    1.06
     advances
    1.05
     ADVANCE
    1.03
    Advance
    1.03
     Advances
    0.96
     Advancement
    0.95
     advancements
    0.94
    Act Density 0.254%

    No Known Activations