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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal expectations and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addons
    -0.17
    èŃľ
    -0.15
    hle
    -0.15
    /lo
    -0.14
    DSL
    -0.14
    ahr
    -0.14
     bananas
    -0.14
    addin
    -0.14
     survival
    -0.13
     Survivor
    -0.13
    POSITIVE LOGITS
     ever
    0.24
     EVER
    0.19
     otherwise
    0.17
     usual
    0.17
     than
    0.16
     any
    0.16
    agal
    0.15
    anos
    0.15
    any
    0.14
    389
    0.14
    Act Density 0.062%

    No Known Activations