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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dependence or reliance on something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aula
    -0.56
    Aula
    -0.51
     aula
    -0.46
    ConstraintMaker
    -0.45
     supr
    -0.45
    </thead>
    -0.44
    \#
    -0.44
     Glaser
    -0.44
    cienti
    -0.43
     laude
    -0.43
    POSITIVE LOGITS
     depend
    0.94
    dependence
    0.93
     dependence
    0.92
     depended
    0.90
    depends
    0.89
     depends
    0.88
     reliance
    0.86
    depend
    0.85
     depender
    0.84
     Depends
    0.83
    Act Density 0.188%

    No Known Activations