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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions of building, developing, or creating systems or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okoj
    -0.16
    ECH
    -0.16
    rikes
    -0.14
    aska
    -0.14
    ãĥ«ãĤ¯
    -0.14
    è¾°
    -0.14
    .Builder
    -0.14
    ajs
    -0.14
    olley
    -0.13
    DAT
    -0.13
    POSITIVE LOGITS
     themselves
    0.37
     thems
    0.17
    NS
    0.17
     their
    0.15
    edback
    0.15
    their
    0.15
    Their
    0.15
     alike
    0.14
    arb
    0.14
    sb
    0.14
    Act Density 0.417%

    No Known Activations