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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by specific locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in [number]" referring to situations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Eva
    -0.73
    rather
    -0.71
    DragonMagazine
    -0.69
    igi
    -0.66
    NOT
    -0.66
     %%
    -0.64
    rien
    -0.63
    oran
    -0.61
    CVE
    -0.60
    esa
    -0.60
    POSITIVE LOGITS
     anymore
    1.69
     nor
    1.43
     any
    1.15
     whatsoever
    1.13
     slightest
    1.12
     anybody
    1.05
     anywhere
    1.01
     anything
    0.97
     necessarily
    0.93
    yet
    0.92
    Act Density 0.319%

    No Known Activations