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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating completeness or wholeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    land
    -0.21
    nde
    -0.18
    der
    -0.18
    la
    -0.16
    rop
    -0.16
    ãĥ¬ãĤ¤
    -0.15
    ichel
    -0.15
    etta
    -0.15
    ette
    -0.15
    roe
    -0.15
    POSITIVE LOGITS
    /full
    0.20
     opposite
    0.17
    å®Įæķ´
    0.17
    idades
    0.15
    IRCLE
    0.15
    ket
    0.15
    palette
    0.15
    ensored
    0.15
    .dsl
    0.15
    ussen
    0.14
    Act Density 0.023%

    No Known Activations