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

    Neuronpedia

    INDEX
    Explanations

    verbs related to improving or manipulating conditions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.93
    MemoryWarning
    -0.92
     vectorielle
    -0.92
     beginnetje
    -0.89
     Houſe
    -0.89
     photolibrary
    -0.89
    AndEndTag
    -0.88
    <?
    -0.86
     CURIAM
    -0.85
     myſelf
    -0.83
    POSITIVE LOGITS
     make
    1.25
     Make
    1.14
    make
    1.13
     makes
    1.12
    Make
    1.07
     MAKE
    1.04
    Makes
    1.03
    makes
    1.02
     making
    1.01
     Makes
    0.97
    Act Density 0.133%

    No Known Activations