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

    Neuronpedia

    INDEX
    Explanations

    names of products or items commonly found in a specific setting or context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scots
    -0.72
    ACTED
    -0.71
     foremost
    -0.69
     Columb
    -0.63
    izations
    -0.61
    TAIN
    -0.61
     Scandinavian
    -0.60
     conspicuous
    -0.60
    ndra
    -0.59
    ritional
    -0.57
    POSITIVE LOGITS
    ombie
    1.37
    arro
    1.25
    hou
    1.25
    alez
    1.13
    ombies
    1.07
    hao
    1.05
    arella
    1.03
    ymes
    0.99
    quez
    0.99
    akura
    0.92
    Act Density 0.937%

    No Known Activations