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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or clauses

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

    Text starting with "If" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    conditional if statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ―――――
    -1.05
     purpoſe
    -0.98
     itſelf
    -0.85
     pleaſure
    -0.84
     ſeveral
    -0.82
     $_"
    -0.80
     Jefus
    -0.80
     Theſe
    -0.79
     Monfieur
    -0.79
     ſind
    -0.78
    POSITIVE LOGITS
     if
    1.22
     If
    1.13
     it
    1.00
    if
    0.99
     you
    0.96
     IF
    0.96
    checkIf
    0.94
     there
    0.92
     they
    0.91
     we
    0.87
    Act Density 0.183%

    No Known Activations