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

    Neuronpedia

    INDEX
    Explanations

    assertions of change or impact on environments, particularly related to safety and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vůbec
    -0.57
    ])));
    -0.57
    Newswire
    -0.52
    stdc
    -0.51
    춤
    -0.48
    tvguidetime
    -0.47
    typeorm
    -0.46
    Diwedd
    -0.46
     présence
    -0.46
    ）.
    -0.45
    POSITIVE LOGITS
    fjspx
    0.76
    danke
    0.69
    ViewFeatures
    0.66
    lloworld
    0.64
    InputBorder
    0.63
    HostException
    0.63
    fromnode
    0.60
    PostConstruct
    0.59
    undy
    0.59
    FunctionFlags
    0.59
    Act Density 0.370%

    No Known Activations