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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating the beginning of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a beginning or initiation of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    visor
    -0.78
    itsch
    -0.76
    aths
    -0.76
    ilty
    -0.73
    otton
    -0.69
    uyomi
    -0.67
    adish
    -0.67
    ules
    -0.65
    onomic
    -0.65
    uled
    -0.64
    POSITIVE LOGITS
     anew
    0.87
    theless
    0.83
     stages
    0.79
    EGIN
    0.72
    LY
    0.70
    ãĤ½
    0.69
    nings
    0.69
    WithNo
    0.66
    externalActionCode
    0.65
    åħī
    0.63
    Act Density 0.026%

    No Known Activations