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

    Neuronpedia

    INDEX
    Explanations

    phrases that include prepositions and linking verbs

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

    "for" or "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by nouns or adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    好きです
    -0.45
    ScopeManager
    -0.44
    +#+#
    -0.42
    }]
    -0.41
    uxxxx
    -0.39
    -0.38
     ['$
    -0.37
    })->
    -0.36
     Phone
    -0.36
    Phone
    -0.36
    POSITIVE LOGITS
     بيها
    0.58
     purpoſe
    0.55
     faſt
    0.53
     houſe
    0.48
     Infórmanos
    0.48
     ſte
    0.48
    FunctionFlags
    0.48
     juſ
    0.46
     ſta
    0.45
     totalité
    0.44
    Act Density 0.455%

    No Known Activations