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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons

    oai_token-act-pair · gpt-3.5-turbo

    instances of lists or enumerations in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %:
    -0.82
    escription
    -0.75
    hig
    -0.74
    gat
    -0.73
    resents
    -0.70
    edom
    -0.68
    icipated
    -0.68
    :[
    -0.68
    sylv
    -0.66
    roup
    -0.66
    POSITIVE LOGITS
     incidentally
    1.41
     alas
    1.40
     anyway
    1.33
     admittedly
    1.21
     eh
    1.11
     yeah
    1.07
     yes
    1.06
     huh
    1.04
     anyways
    1.03
     presumably
    1.01
    Act Density 0.217%

    No Known Activations