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

    Neuronpedia

    INDEX
    Explanations

    potential conditional statements or expressions of uncertainty

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

    "maybe"

    np_acts-logits-general · gemini-2.0-flash

    introduces possibility or speculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.75
    AndEndTag
    -0.74
     himſelf
    -0.72
     itſelf
    -0.71
     pleaſure
    -0.71
     iconFacebook
    -0.66
    UIControlState
    -0.66
     Jefus
    -0.66
     ―――――
    -0.65
     respectivamente
    -0.64
    POSITIVE LOGITS
    anskje
    1.04
     someday
    0.88
     maybe
    0.84
    maybe
    0.80
    Maybe
    0.74
     Maybe
    0.73
     even
    0.69
     something
    0.64
     perhaps
    0.61
     someone
    0.61
    Act Density 0.067%

    No Known Activations