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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and linking phrases that indicate a connection or continuation of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.71
    adecimal
    -0.69
     msglen
    -0.66
    ʺ
    -0.65
    Gruß
    -0.64
    tems
    -0.63
    felf
    -0.63
     neceff
    -0.62
     (§
    -0.61
     fubject
    -0.61
    POSITIVE LOGITS
     we
    0.71
     I
    0.67
     something
    0.66
     you
    0.64
     everybody
    0.64
     it
    0.64
     everyone
    0.63
     And
    0.62
     if
    0.60
     there
    0.59
    Act Density 0.400%

    No Known Activations