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

    Neuronpedia

    INDEX
    Explanations

    exceptions or exclusions in a list

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ancest
    -0.63
    ore
    -0.61
     desper
    -0.60
     NX
    -0.59
     MEP
    -0.59
    anche
    -0.57
     ger
    -0.57
    urry
    -0.56
     neighb
    -0.56
    otted
    -0.55
    POSITIVE LOGITS
     exceptions
    0.82
    ngth
    0.76
     exception
    0.71
    blance
    0.67
    Thumbnail
    0.65
    âĶĢâĶĢâĶĢâĶĢ
    0.65
    epad
    0.64
    UFC
    0.64
    dylib
    0.63
    osaurs
    0.61
    Act Density 0.020%

    No Known Activations