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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the contraction "I've" and its variants, indicating personal experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lc
    -0.16
    CallCheck
    -0.15
     not
    -0.15
    ulse
    -0.14
    icerca
    -0.14
    hof
    -0.14
    lacak
    -0.14
    ÃŃte
    -0.14
    nett
    -0.14
    oton
    -0.14
    POSITIVE LOGITS
     been
    0.21
     got
    0.21
     Been
    0.20
    been
    0.18
     Got
    0.17
    Been
    0.17
    Got
    0.17
    amp
    0.16
     BEEN
    0.16
     GOT
    0.16
    Act Density 0.067%

    No Known Activations