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

    Neuronpedia

    INDEX
    Explanations

    references to chains or sequences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.94
    parsedMessage
    -0.84
    ########.
    -0.79
    AISSEE
    -0.79
     فريبيس
    -0.77
    IUrlHelper
    -0.74
    <unused41>
    -0.74
     يتيمه
    -0.74
    <unused79>
    -0.73
    <unused3>
    -0.73
    POSITIVE LOGITS
     chain
    0.82
     health
    0.69
     chains
    0.62
     Chain
    0.59
     healthy
    0.58
     hair
    0.57
     chair
    0.56
     search
    0.52
    Chain
    0.51
     member
    0.49
    Act Density 0.247%

    No Known Activations