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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal preference or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.66
    verwijspagina
    -0.65
     laço
    -0.59
    holm
    -0.57
     Aware
    -0.55
    ión
    -0.55
     occ
    -0.54
     Ashby
    -0.53
    loop
    -0.53
    heder
    -0.52
    POSITIVE LOGITS
    Portale
    0.86
    AnchorStyles
    0.76
     DriverManager
    0.71
     a
    0.69
    POSSIBLE
    0.68
    ">${
    0.67
    odziel
    0.67
    ✨:
    0.67
    THINK
    0.66
    andExpect
    0.66
    Act Density 0.047%

    No Known Activations