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

    Neuronpedia

    INDEX
    Explanations

    elements related to transformation and versatility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¿®
    -0.13
     additions
    -0.13
    jsp
    -0.13
     expansions
    -0.13
    urdy
    -0.12
    etak
    -0.12
     refine
    -0.12
     refinement
    -0.12
    expanded
    -0.12
    compress
    -0.12
    POSITIVE LOGITS
     change
    0.67
     switch
    0.66
     switching
    0.63
     changing
    0.63
    change
    0.61
    switch
    0.61
    -switch
    0.59
     Switch
    0.59
     switches
    0.59
     switched
    0.58
    Act Density 0.288%

    No Known Activations