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

    Neuronpedia

    INDEX
    Explanations

    descriptions of trails or paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.37
    ────────
    -0.35
     standing
    -0.34
    Compound
    -0.34
    complexContent
    -0.33
     STAND
    -0.33
     đứng
    -0.32
     Compound
    -0.32
     стоя
    -0.31
    Achie
    -0.31
    POSITIVE LOGITS
     running
    1.25
     connecting
    1.15
     linking
    1.12
     traversing
    1.12
    running
    1.08
    Running
    1.02
     Running
    1.02
     traverses
    1.00
     runs
    0.98
    connecting
    0.97
    Act Density 0.835%

    No Known Activations