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

    Neuronpedia

    INDEX
    Explanations

    activities related to mystery-solving and exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åħ¬è·¯
    -0.14
    Drivers
    -0.13
    ë³µì§Ģ
    -0.13
     Plains
    -0.13
    _MOUNT
    -0.12
    orthand
    -0.12
     highways
    -0.12
     Fisheries
    -0.12
     Territories
    -0.12
    itol
    -0.12
    POSITIVE LOGITS
     escape
    0.55
     Escape
    0.52
    Escape
    0.45
    escape
    0.43
     escapes
    0.42
     escaping
    0.40
    .Escape
    0.38
     Esc
    0.37
    _escape
    0.37
     escap
    0.36
    Act Density 0.013%

    No Known Activations