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

    Neuronpedia

    INDEX
    Explanations

    text related to scraps or scavenge

    oai_token-act-pair · gpt-3.5-turbo

    references to scraps and scavenging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -0.79
    igmatic
    -0.74
    secut
    -0.73
     attentive
    -0.69
     conspicuous
    -0.67
    iyah
    -0.66
     uncond
    -0.66
    cest
    -0.65
    secution
    -0.65
    vironments
    -0.64
    POSITIVE LOGITS
    ãĤ¡
    0.85
    atted
    0.84
    bones
    0.84
    shaw
    0.84
    hire
    0.84
    yard
    0.83
    ree
    0.81
     heap
    0.80
    enhagen
    0.79
    dump
    0.76
    Act Density 0.022%

    No Known Activations