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

    Neuronpedia

    INDEX
    Explanations

    terms related to inter-related processes or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toJson
    -0.71
    <?>>
    -0.70
     vägen
    -0.67
     تضيفلها
    -0.66
    chtigkeit
    -0.66
     öv
    -0.65
     clazz
    -0.65
     vouloir
    -0.64
     frutos
    -0.64
     bygga
    -0.63
    POSITIVE LOGITS
     INTER
    1.34
     inter
    1.26
    INTER
    1.25
     Inter
    1.21
    Inter
    1.15
     Inters
    1.07
     interp
    1.06
     inters
    0.99
     interns
    0.97
     interconnect
    0.95
    Act Density 0.111%

    No Known Activations