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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to academic or educational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    specific phrases or constructs indicating actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Den + Danish names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.88
     weißem
    -0.75
     ſche
    -0.75
     Jefus
    -0.74
     lenker
    -0.73
     pleaſure
    -0.72
     canina
    -0.71
     poffible
    -0.69
     malheure
    -0.69
     poffe
    -0.68
    POSITIVE LOGITS
    __(/*!
    0.59
     primit
    0.52
    liothèque
    0.52
    ;'>
    0.52
     very
    0.50
     robust
    0.49
    cionario
    0.48
    dataclass
    0.47
     great
    0.47
    ;">
    0.47
    Act Density 0.025%

    No Known Activations