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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that connect phrases or clauses in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.69
    ſelves
    -0.59
    ſelf
    -0.57
     poffe
    -0.55
     fubject
    -0.54
     ſtate
    -0.52
     ftate
    -0.51
     myſelf
    -0.51
     poffible
    -0.51
    ContentAlignment
    -0.49
    POSITIVE LOGITS
     I
    0.42
    blah
    0.42
     Mus
    0.39
    umball
    0.39
    亥
    0.38
     בלי
    0.37
     freaked
    0.37
     funny
    0.37
     chees
    0.37
     Aufen
    0.37
    Act Density 0.444%

    No Known Activations