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

    Neuronpedia

    INDEX
    Explanations

    references to children

    oai_token-act-pair · gpt-3.5-turbo

    references to children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ced
    -0.69
    PROV
    -0.67
    ENCE
    -0.66
    ATION
    -0.66
    ãĥ´ãĤ¡
    -0.65
     comm
    -0.64
    COMPLE
    -0.63
    itation
    -0.63
     manifold
    -0.62
    ATIVE
    -0.60
    POSITIVE LOGITS
    ishly
    0.99
    children
    0.90
     orphan
    0.81
    child
    0.79
    sle
    0.78
    ynski
    0.78
    ults
    0.76
     Icar
    0.75
    riages
    0.74
     born
    0.74
    Act Density 0.037%

    No Known Activations