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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Proceed
    -0.78
    ortmund
    -0.77
    ileaks
    -0.75
    ð
    -0.75
    icum
    -0.73
    ithe
    -0.72
    inav
    -0.70
    reply
    -0.69
    ESE
    -0.68
    icip
    -0.67
    POSITIVE LOGITS
     gonna
    0.94
     definitely
    0.83
     everywhere
    0.83
     not
    0.83
     certainly
    0.82
     supposed
    0.77
     relentless
    0.76
     contagious
    0.75
     nowhere
    0.74
     always
    0.74
    Act Density 0.133%

    No Known Activations