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

    Neuronpedia

    INDEX
    Explanations

    text related to spatial concepts or locations

    oai_token-act-pair · gpt-3.5-turbo

    indicators of urgency or critical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĦ
    -0.64
     Canaver
    -0.60
    ãĥ¯ãĥ³
    -0.60
    DCS
    -0.59
    ãĤ¢ãĥ«
    -0.57
    ":{"
    -0.55
    NSA
    -0.54
    IDENT
    -0.54
    Ħ¢
    -0.54
    issance
    -0.54
    POSITIVE LOGITS
     theirs
    0.65
    .;
    0.63
     pts
    0.55
     tho
    0.52
     meanwhile
    0.51
    onite
    0.50
    %;
    0.50
    ;}
    0.50
    ;
    0.48
     [];
    0.48
    Act Density 2.022%

    No Known Activations