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

    Neuronpedia

    INDEX
    Explanations

    phrases related to trying or experimenting with different things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏįÏĢ
    -0.18
    MBER
    -0.17
    egal
    -0.16
    piel
    -0.16
    uito
    -0.15
    upro
    -0.14
    emer
    -0.14
    ernote
    -0.14
    ledi
    -0.14
    cu
    -0.14
    POSITIVE LOGITS
    試
    0.17
    oulos
    0.16
    aday
    0.15
    icle
    0.14
     Maj
    0.14
    ald
    0.14
    lington
    0.14
     Plasma
    0.14
    LR
    0.14
    123
    0.14
    Act Density 0.082%

    No Known Activations