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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onec
    -0.15
    shiv
    -0.15
    .ov
    -0.15
     correlate
    -0.14
     reckon
    -0.14
    .opend
    -0.14
    á»ħ
    -0.14
    iar
    -0.14
    ccione
    -0.14
    ohn
    -0.13
    POSITIVE LOGITS
     effect
    0.21
     pattern
    0.19
     effects
    0.18
     phenomenon
    0.17
     trend
    0.17
     patterns
    0.17
    tent
    0.16
     artifact
    0.16
     Pattern
    0.16
     finding
    0.16
    Act Density 0.197%

    No Known Activations