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

    Neuronpedia

    INDEX
    Explanations

    names and titles associated with significant figures or entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISTORY
    -0.15
    624
    -0.14
    едак
    -0.14
    461
    -0.14
    .intellij
    -0.13
    ÑĪкÑĥ
    -0.13
     karÅŁÄ±lık
    -0.13
    agenda
    -0.13
    eras
    -0.13
    iyel
    -0.13
    POSITIVE LOGITS
     publicly
    0.31
     statements
    0.26
     stated
    0.25
     statement
    0.24
     public
    0.23
    public
    0.21
    statement
    0.20
     Statements
    0.20
     stmt
    0.20
     said
    0.19
    Act Density 0.441%

    No Known Activations