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

    Neuronpedia

    INDEX
    Explanations

    derivatives or variations of the verb "erase."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yne
    -0.21
    ville
    -0.20
    ril
    -0.18
    ARAM
    -0.18
    t
    -0.17
    rif
    -0.17
    =-=-=-=-
    -0.16
    yre
    -0.16
    ray
    -0.15
    VILLE
    -0.15
    POSITIVE LOGITS
    oding
    0.36
    oded
    0.35
    adic
    0.32
    asure
    0.29
    asures
    0.26
    asing
    0.26
    ode
    0.26
    odes
    0.25
    ector
    0.24
    atic
    0.23
    Act Density 0.010%

    No Known Activations