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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or commands

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

    Comes before an infinitive verb

    np_acts-logits-general · gemini-2.0-flash

    sentences expressing obligation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.66
     CommonModule
    -0.56
     gewünschten
    -0.56
    vety
    -0.56
    //
    -0.56
    WebVitals
    -0.55
     direta
    -0.54
     bedoeld
    -0.54
     invers
    -0.53
    ाइल
    -0.53
    POSITIVE LOGITS
    ArgsConstructor
    0.76
     necesariamente
    0.75
     necessariamente
    0.71
    才能
    0.71
     wait
    0.67
     must
    0.60
     go
    0.59
     necessarily
    0.59
    Gotta
    0.59
     contend
    0.58
    Act Density 0.183%

    No Known Activations