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

    Neuronpedia

    INDEX
    Explanations

    phrases containing hypothetical situations or conditional clauses

    oai_token-act-pair · gpt-3.5-turbo

    instances of hypothetical situations or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.77
    DX
    -0.77
    ©¶æ¥µ
    -0.72
    enos
    -0.67
    often
    -0.66
    ighting
    -0.65
    IDA
    -0.65
    ema
    -0.62
    chin
    -0.62
    Contents
    -0.61
    POSITIVE LOGITS
     beforehand
    0.89
     sooner
    0.85
     hypot
    0.78
     somehow
    0.72
     someday
    0.72
     tomorrow
    0.70
     existed
    0.67
     hadn
    0.64
    essor
    0.64
     somewhere
    0.64
    Act Density 0.474%

    No Known Activations