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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidance and support for beginners and those seeking advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     obfer
    -0.58
     sonno
    -0.58
     Descub
    -0.57
    ſelf
    -0.55
    ugal
    -0.54
    
    -0.54
     poffe
    -0.53
     Efq
    -0.53
     chofe
    -0.53
     antwoord
    -0.52
    POSITIVE LOGITS
     get
    0.68
     flesh
    0.59
    figure
    0.58
     really
    0.58
     figure
    0.57
     solidify
    0.57
     virkelig
    0.56
     gets
    0.55
    NamedQuery
    0.53
    SpringRunner
    0.53
    Act Density 0.362%

    No Known Activations