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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sharing thoughts and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brit
    -0.15
    hv
    -0.14
    ijo
    -0.14
     Lew
    -0.14
    aro
    -0.14
    indi
    -0.14
    ovable
    -0.14
     hv
    -0.13
    brook
    -0.13
    æ¸Ī
    -0.13
    POSITIVE LOGITS
     tonight
    0.21
     here
    0.19
     myself
    0.17
     because
    0.16
     today
    0.15
    IVER
    0.15
    ISK
    0.15
     buflen
    0.15
    rophe
    0.15
    here
    0.15
    Act Density 0.189%

    No Known Activations