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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions related to feelings and perceptions

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

    that can be relative pronouns or possessive adjectives

    np_acts-logits-general · gemini-2.0-flash

    who or whom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -1.03
    DoubleQuotes
    -0.98
     виправивши
    -0.88
    sidemargin
    -0.85
    TypedDataSet
    -0.84
    several
    -0.84
    BeginInit
    -0.84
    PerformLayout
    -0.84
     several
    -0.82
    parsedMessage
    -0.82
    POSITIVE LOGITS
     who
    0.66
     whom
    0.64
     którzy
    0.63
     their
    0.62
     kteří
    0.61
     or
    0.53
     themselves
    0.49
    whom
    0.48
    或者
    0.46
     THEIR
    0.46
    Act Density 0.459%

    No Known Activations