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

    Neuronpedia

    INDEX
    Explanations

    assertions and requests related to actions and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.79
     <<<<<<<<<<<<<<
    -0.73
    ).
    -0.73
    ”.
    -0.69
    ".
    -0.68
    “.
    -0.65
    }}$.
    -0.64
    AccessorTable
    -0.64
    󠁿
    -0.62
    '.
    -0.62
    POSITIVE LOGITS
     any
    0.88
     anything
    0.87
    anything
    0.86
     quelconque
    0.83
     aught
    0.75
    的话
    0.73
     quelcon
    0.71
     yoksa
    0.71
     ANY
    0.69
    ใด
    0.68
    Act Density 0.334%

    No Known Activations