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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating firmness or resilience in behavior or stance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rè
    -0.66
    })));
    -0.64
     Nark
    -0.64
    numerusform
    -0.57
    PyTuple
    -0.53
    ordning
    -0.52
    zao
    -0.52
     geçir
    -0.51
    НОСТИ
    -0.50
    "):
    -0.50
    POSITIVE LOGITS
     STAND
    1.16
     Stand
    1.16
     stand
    1.16
     stands
    1.14
     Stands
    1.12
    Stand
    1.09
     stood
    1.09
     standing
    1.08
    STAND
    1.03
     debout
    1.02
    Act Density 0.052%

    No Known Activations