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

    Neuronpedia

    INDEX
    Explanations

    concepts and suggestions related to "ideas."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.46
     ſtate
    -0.44
     ſever
    -0.43
     Administrativna
    -0.43
     canst
    -0.42
    yelidikan
    -0.40
     Anſ
    -0.40
     feroit
    -0.39
     juſ
    -0.39
     vœ
    -0.39
    POSITIVE LOGITS
     Term
    0.76
     TERM
    0.74
     Terms
    0.72
     terminate
    0.68
    Term
    0.67
     Termin
    0.66
    termin
    0.65
     termination
    0.65
     terminates
    0.65
     idea
    0.65
    Act Density 0.227%

    No Known Activations