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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .extern
    -0.16
     ain
    -0.15
    ters
    -0.15
    .cg
    -0.14
    .createClass
    -0.14
    .Attach
    -0.14
     اØ
    -0.14
     unic
    -0.13
    oring
    -0.13
    ern
    -0.13
    POSITIVE LOGITS
    ensa
    0.19
     here
    0.19
    antha
    0.17
     goes
    0.17
     she
    0.16
     Here
    0.15
     HERE
    0.15
    orest
    0.15
    undry
    0.15
    raud
    0.15
    Act Density 0.031%

    No Known Activations