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

    Neuronpedia

    INDEX
    Explanations

    phrases related to methods, techniques, and tools

    oai_token-act-pair · gpt-3.5-turbo

    techniques and methods related to advanced algorithms and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.76
     coff
    -0.57
    sle
    -0.55
    lings
    -0.52
    vin
    -0.51
    itol
    -0.51
     Stamp
    -0.50
    cup
    -0.50
    rament
    -0.50
    hoff
    -0.50
    POSITIVE LOGITS
    pmwiki
    0.71
     devised
    0.65
     designed
    0.63
     whereby
    0.60
     adaptive
    0.60
     patented
    0.58
     targeting
    0.58
     recursive
    0.56
     aimed
    0.56
     pioneered
    0.55
    Act Density 1.004%

    No Known Activations