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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    окол
    -0.15
    оÑĢоз
    -0.15
    umd
    -0.15
    -prepend
    -0.14
    owards
    -0.14
    omers
    -0.14
    undy
    -0.14
    iban
    -0.14
    ãģ¨ãģĨ
    -0.13
    éļĽ
    -0.13
    POSITIVE LOGITS
     anything
    0.42
     anyone
    0.36
     anybody
    0.35
    anything
    0.34
     ever
    0.31
     nothing
    0.30
     Anything
    0.29
     memory
    0.28
    Anything
    0.27
    eel
    0.27
    Act Density 0.087%

    No Known Activations