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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to decision-making or planning in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alu
    -0.15
     assignable
    -0.14
    æĶ¾
    -0.14
    baum
    -0.14
    odel
    -0.13
    óc
    -0.13
    icens
    -0.13
    (ignore
    -0.13
    dex
    -0.13
    ISON
    -0.13
    POSITIVE LOGITS
     aprove
    0.25
    åĪ©çĶ¨
    0.24
     benefited
    0.24
     benefit
    0.24
     vyu
    0.23
     benef
    0.22
     drawing
    0.22
     Drawing
    0.22
     táºŃn
    0.22
     tapping
    0.22
    Act Density 0.022%

    No Known Activations