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

    Neuronpedia

    INDEX
    Explanations

    comparative words or phrases indicating similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOUR
    -0.16
    esson
    -0.16
    /raw
    -0.15
    byn
    -0.15
    縮
    -0.14
    gor
    -0.14
    रण
    -0.13
    баÑĩ
    -0.13
     stripslashes
    -0.13
    grily
    -0.13
    POSITIVE LOGITS
    ród
    0.15
    rch
    0.15
    edy
    0.15
    orz
    0.14
    681
    0.14
     witness
    0.14
     Wilde
    0.13
    tle
    0.13
    åį
    0.13
    onz
    0.13
    Act Density 0.036%

    No Known Activations