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

    Neuronpedia

    INDEX
    Explanations

    expressions and concepts related to knowledge and understanding processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izo
    -0.15
    /fw
    -0.15
    ioni
    -0.15
    gebra
    -0.15
    obo
    -0.15
    kel
    -0.15
    ogle
    -0.14
    aro
    -0.14
    alon
    -0.14
     Duch
    -0.14
    POSITIVE LOGITS
     so
    0.34
     sorts
    0.30
     sort
    0.23
     proverb
    0.21
     as
    0.21
     essentially
    0.20
     manner
    0.19
    -to
    0.19
     basically
    0.18
    so
    0.18
    Act Density 0.191%

    No Known Activations