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

    Neuronpedia

    INDEX
    Explanations

    the word "most" in various contexts

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

    Follows "most" and indicates likelihood or commonality

    np_acts-logits-general · gemini-2.0-flash

    most followed by adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.78
     صوتيه
    -0.76
     وتسجيلات
    -0.73
     tantôt
    -0.69
    MigrationBuilder
    -0.67
     AssemblyTitle
    -0.64
     Autorizaciones
    -0.62
     quelquefois
    -0.61
     blessés
    -0.60
    elemField
    -0.60
    POSITIVE LOGITS
     likely
    1.30
     importantly
    1.12
     notably
    0.93
    likely
    0.93
     Likely
    0.84
     assuredly
    0.81
     certainly
    0.77
     often
    0.75
    Likely
    0.75
     commonly
    0.71
    Act Density 0.084%

    No Known Activations