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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or phrases involving "if."

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

    "If" followed by pronouns/determiners

    np_acts-logits-general · gemini-2.0-flash

    if followed by subject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.86
     Efq
    -0.79
     myſelf
    -0.79
     itſelf
    -0.78
     <<<<<<<<<<<<<<
    -0.76
    헌
    -0.73
     whoſe
    -0.72
    شهاد
    -0.70
     Majefty
    -0.70
    extAlignment
    -0.69
    POSITIVE LOGITS
     anything
    0.77
     anyone
    0.70
     anybody
    0.66
    anything
    0.61
    Anybody
    0.59
    Anyone
    0.58
    anyone
    0.57
     hadn
    0.56
     Anyone
    0.55
     you
    0.55
    Act Density 0.116%

    No Known Activations