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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and phrases indicating possibility or capability

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

    Following "can" or "be"

    np_acts-logits-general · gemini-2.0-flash

    can followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    providedIn
    -0.80
    bootstrapcdn
    -0.72
    principalTable
    -0.72
    enumi
    -0.67
    ValueStyle
    -0.67
     @"/
    -0.66
    MigrationBuilder
    -0.61
     magique
    -0.60
    WindowConstants
    -0.60
    +#+#
    -0.58
    POSITIVE LOGITS
     think
    0.63
     thought
    0.59
     easily
    0.59
     readily
    0.56
     theoretically
    0.55
     equivalently
    0.55
     XCTest
    0.53
     alternatively
    0.53
     conceivably
    0.52
     conveniently
    0.51
    Act Density 0.531%

    No Known Activations