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

    Neuronpedia

    INDEX
    Explanations

    references to membership or participation in organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     totaled
    -0.16
    vertiser
    -0.14
     totaling
    -0.14
    coni
    -0.14
    [assembly
    -0.14
    ripp
    -0.14
    alk
    -0.14
    ål
    -0.14
    ots
    -0.13
    ĶåĽŀ
    -0.13
    POSITIVE LOGITS
    ãģĨãģ¡
    0.38
     mostly
    0.29
     majority
    0.26
    åħ¶ä¸Ń
    0.25
     including
    0.25
     most
    0.24
    mostly
    0.24
     ëĮĢë¶Ģë¶Ħ
    0.24
    ï¼Įåħ¶ä¸Ń
    0.23
     davon
    0.23
    Act Density 0.193%

    No Known Activations