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

    Neuronpedia

    INDEX
    Explanations

    expressions of concern or indifference towards various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anner
    -0.07
    کارÛĮ
    -0.07
    ople
    -0.07
    awa
    -0.06
    essim
    -0.06
    ersen
    -0.06
    sted
    -0.06
    ions
    -0.06
    IDDLE
    -0.06
    opia
    -0.06
    POSITIVE LOGITS
     whether
    0.08
    .cbo
    0.07
    ngr
    0.07
    .chk
    0.07
    undos
    0.07
     retr
    0.07
    endir
    0.07
    lyn
    0.07
    ledged
    0.06
    ingly
    0.06
    Act Density 0.007%

    No Known Activations