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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or moments in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EqualsAnd
    -0.62
     resourceCulture
    -0.58
    Hentet
    -0.53
    PageRoute
    -0.53
     Sad
    -0.52
    andExpect
    -0.51
     সে
    -0.51
    -0.51
    Awe
    -0.50
     Beg
    -0.49
    POSITIVE LOGITS
     Theſe
    0.95
     Efq
    0.93
     myſelf
    0.79
     Monfieur
    0.77
     himſelf
    0.72
     themſelves
    0.70
     itſelf
    0.70
     theſe
    0.69
     voici
    0.67
     Houſe
    0.65
    Act Density 0.456%

    No Known Activations