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

    Neuronpedia

    INDEX
    Explanations

    references to the term "ho" and its variations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    новништво
    -0.47
    geslacht
    -0.39
     Volunt
    -0.39
    SourceChecksum
    -0.39
     sơ
    -0.37
    depend
    -0.37
    chauff
    -0.37
     INDUSTR
    -0.37
    thenReturn
    -0.37
     revol
    -0.36
    POSITIVE LOGITS
     ho
    1.79
     Ho
    1.61
    Ho
    1.52
    ho
    1.47
    HO
    1.00
     HO
    0.91
     typelib
    0.69
     hoist
    0.65
     hoard
    0.64
    hoho
    0.64
    Act Density 0.158%

    No Known Activations