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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons and conditional statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Inv
    -0.15
    hood
    -0.15
    indsight
    -0.15
    579
    -0.15
    į¨
    -0.14
     Bio
    -0.14
    inh
    -0.14
    adian
    -0.14
    ney
    -0.14
    Probe
    -0.14
    POSITIVE LOGITS
    cha
    0.17
    anova
    0.15
    äºİ
    0.15
    omens
    0.14
    aggable
    0.14
    uber
    0.14
    than
    0.14
    SSIP
    0.14
    æīĢ
    0.13
     than
    0.13
    Act Density 0.048%

    No Known Activations