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

    Neuronpedia

    INDEX
    Explanations

    references to hiding or concealing objects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nakalista
    -0.79
     defaultstate
    -0.74
    PerformLayout
    -0.60
    Browsable
    -0.59
    ArgsConstructor
    -0.59
     himo
    -0.58
    VersionUID
    -0.57
     <",
    -0.56
    جمعیت
    -0.56
    SequentialGroup
    -0.55
    POSITIVE LOGITS
     undetected
    0.63
     secretly
    0.60
     sneaking
    0.55
     hope
    0.52
    BagLayout
    0.51
    sne
    0.48
     sneak
    0.47
     clandestine
    0.46
     stealth
    0.46
     keber
    0.46
    Act Density 0.087%

    No Known Activations