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

    Neuronpedia

    INDEX
    Explanations

    symbols and unusual characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.17
    irma
    -0.16
    .Restrict
    -0.15
    _atomic
    -0.14
    _ATOM
    -0.14
    SAT
    -0.14
    izard
    -0.14
    spender
    -0.14
    orning
    -0.14
    менÑĪ
    -0.14
    POSITIVE LOGITS
     hit
    0.18
     Fair
    0.17
     heat
    0.16
     therm
    0.16
     Kurul
    0.16
     Mac
    0.15
     Ruf
    0.15
    ither
    0.15
     fair
    0.15
     Mitchell
    0.15
    Act Density 0.005%

    No Known Activations