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

    Neuronpedia

    INDEX
    Explanations

    phrases related to materials or resources

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with quantity and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iso
    -0.63
    hett
    -0.60
    halla
    -0.58
    SpaceEngineers
    -0.58
    ItemTracker
    -0.57
    onne
    -0.56
    media
    -0.55
     greets
    -0.55
    Prop
    -0.54
    Drive
    -0.53
    POSITIVE LOGITS
     sorts
    1.36
     varying
    1.27
    course
    1.17
     theirs
    1.06
     course
    1.02
     dubious
    0.97
     comparable
    0.97
     questionable
    0.96
     ours
    0.96
     hers
    0.96
    Act Density 0.148%

    No Known Activations