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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "their" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pins
    -0.63
     zamanda
    -0.61
    endphp
    -0.60
    cuts
    -0.54
    ituary
    -0.54
     afstand
    -0.52
    phalt
    -0.51
     vowels
    -0.51
     Chas
    -0.50
     Jind
    -0.50
    POSITIVE LOGITS
     their
    2.46
    Their
    2.36
     Their
    2.22
    their
    2.21
     themselves
    2.12
     THEIR
    2.00
     they
    1.93
    themselves
    1.80
     They
    1.69
     theirs
    1.67
    Act Density 0.239%

    No Known Activations