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

    Neuronpedia

    INDEX
    Explanations

    specific scientific terminology and important statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    both
    -0.47
     finally
    -0.46
    finally
    -0.45
     respectively
    -0.44
     both
    -0.43
    especially
    -0.43
     particularmente
    -0.42
     especially
    -0.40
    from
    -0.40
    this
    -0.39
    POSITIVE LOGITS
    0.72
    各样的
    0.71
    <pad>
    0.70
    bildtitel
    0.70
     Dieſe
    0.69
    OGND
    0.69
    <unused43>
    0.69
    <unused76>
    0.68
    fjspx
    0.68
    <unused20>
    0.68
    Act Density 2.279%

    No Known Activations