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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce contrasting information or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enstein
    -0.15
    _PD
    -0.15
    abbo
    -0.15
    iliz
    -0.15
     اÙĦاØŃ
    -0.14
    eniz
    -0.14
    áli
    -0.14
    ilin
    -0.14
    Xd
    -0.14
    :invoke
    -0.14
    POSITIVE LOGITS
     Spinner
    0.14
    arak
    0.14
     nue
    0.14
     recursively
    0.14
    ulle
    0.14
    /*****************************************************************************↵
    0.13
     Leaf
    0.13
     Scre
    0.13
    issance
    0.13
    ure
    0.13
    Act Density 0.079%

    No Known Activations